Showing 1–17 of 17 results for author: Shou, W

An automated method of identifying incorrectly labelled images based on the sequences of loss functions of deep learning networks

Authors: Zhipeng Zhang, Wenhui Shou, Wengting Ma, Dongjia Xing, Qingqing Xu, Li-Qun Xu, Qingxia Fan, Ling Xu

Abstract: Deep learning is widely applied in medical image analysis, but up to 10% of manually labelled images may be incorrect, degrading model performance. This paper proposes an automated method to identify incorrectly labelled medical images by analyzing sequences of loss functions from deep learning classification networks over multiple training epochs. Identified images can be reviewed and relabelled… ▽ More Deep learning is widely applied in medical image analysis, but up to 10% of manually labelled images may be incorrect, degrading model performance. This paper proposes an automated method to identify incorrectly labelled medical images by analyzing sequences of loss functions from deep learning classification networks over multiple training epochs. Identified images can be reviewed and relabelled by experts, improving dataset quality and model performance. Two experiments validate the method on a fundus image dataset for referable diabetic retinopathy screening. In the first, 6% (648) of 10,788 gold-standard labels were intentionally flipped. The method identified 75.31% (488) of the flipped samples, with only 4.85% (492) false positives among correctly labelled samples. In the second, reviewing and correcting the 980 identified samples (9.1% of the dataset) and retraining the model improved best accuracy on an independent test set from 95.93% (with 6% label noise) to 96.50% (with 1.5% noise), approaching the ideal 96.57% (with 0% noise). The results demonstrate the method's effectiveness in improving model performance through automated label quality control. △ Less

Submitted 1 July, 2026; originally announced July 2026.

Comments: Presented at the 6th EAI International Conference on IoT as a Service (IoTaaS 2020). Published by Springer in LNICST, vol 346, 2021

Journal ref: in IoT as a Service, 6th EAI Int. Conf. (IoTaaS 2020), LNICST 346, Springer, 2021, pp. 261-269

EquiBim: Learning Symmetry-Equivariant Policy for Bimanual Manipulation

Authors: Zhiyuan Zhang, Aditya Mohan, Seungho Han, Wan Shou, Dongyi Wang, Yu She

Abstract: Robotic imitation learning has achieved impressive success in learning complex manipulation behaviors from demonstrations. However, many existing robot learning methods do not explicitly account for the physical symmetries of robotic systems, often resulting in asymmetric or inconsistent behaviors under symmetric observations. This limitation is particularly pronounced in dual-arm manipulation, wh… ▽ More Robotic imitation learning has achieved impressive success in learning complex manipulation behaviors from demonstrations. However, many existing robot learning methods do not explicitly account for the physical symmetries of robotic systems, often resulting in asymmetric or inconsistent behaviors under symmetric observations. This limitation is particularly pronounced in dual-arm manipulation, where bilateral symmetry is inherent to both the robot morphology and the structure of many tasks. In this paper, we introduce EquiBim, a symmetry-equivariant policy learning framework for bimanual manipulation that enforces bilateral equivariance between observations and actions during training. Our approach formulates physical symmetry as a group action on both observation and action spaces, and imposes an equivariance constraint on policy predictions under symmetric transformations. The framework is model-agnostic and can be seamlessly integrated into a wide range of imitation learning pipelines with diverse observation modalities and action representations, including point cloud-based and image-based policies, as well as both end-effector-space and joint-space parameterizations. We evaluate EquiBim on RoboTwin, a dual-arm robotic platform with symmetric kinematics, and evaluate it across diverse observation and action configurations in simulation. We further validate the approach on a real-world dual-arm system. Across both simulation and physical experiments, our method consistently improves performance and robustness under distribution shifts. These results suggest that explicitly enforcing physical symmetry provides a simple yet effective inductive bias for bimanual robot learning. △ Less

Submitted 20 July, 2026; v1 submitted 9 March, 2026; originally announced March 2026.

Comments: Accepted to IROS 2026. Project page: https://zhangzhiyuanzhang.github.io/equibim-website/

Exploring Metal Additive Manufacturing in Martian Atmospheric Environments

Authors: Zane Mebruer, Wan Shou

Abstract: In-space manufacturing is essential for achieving long-term planetary colonization, particularly on Mars, where material transport from Earth is both costly and logistically restrictive. Traditional subtractive manufacturing methods are highly equipment-, energy-, and material-intensive, making additive manufacturing (AM) a more practical and sustainable alternative for extraterrestrial production… ▽ More In-space manufacturing is essential for achieving long-term planetary colonization, particularly on Mars, where material transport from Earth is both costly and logistically restrictive. Traditional subtractive manufacturing methods are highly equipment-, energy-, and material-intensive, making additive manufacturing (AM) a more practical and sustainable alternative for extraterrestrial production. Among various AM technologies, selective laser melting (SLM) stands out due to its exceptional versatility, precision, and capability to produce dense metallic parts with complex geometries. However, conventional SLM processes rely heavily on inert argon environments to prevent oxidation and ensure high-quality part formation, conditions that are difficult to reproduce on Mars. This study investigates the feasibility of using carbon dioxide (CO2), which makes up over 95% of the Martian atmosphere, as a potential substitute for argon in SLM. Single-track and two-dimensional 316L stainless steel specimens were fabricated under argon, CO2, and ambient air environments with a wide range of laser parameters to evaluate the influence of atmospheric composition on surface morphology, microstructural cohesion, and oxidation behavior. The results reveal that no single parameter controls the overall part quality; rather, a balance of parameters is essential to maintain thermal equilibrium during fabrication. Although parts produced in CO2 exhibited slightly inferior surface finish, cohesion, and oxidation resistance compared to argon, they performed significantly better than those fabricated in ambient air. These findings suggest that CO2-assisted SLM could enable sustainable in situ manufacturing on Mars and may also serve as a cost-effective alternative shielding gas for terrestrial applications. △ Less

Submitted 3 January, 2026; originally announced January 2026.

Microscale selective laser sintering of Cu nanoparticles with a short-wavelength nanosecond laser

Authors: Youwen Liang, Bo Shen, Wan Shou

Abstract: Microscale additive manufacturing of reflective copper is becoming increasingly important for microelectronics and microcomputers, due to its excellent electrical and thermal conductivity. Yet, it remains challenging for state-of-the-art commercial metal 3D printers to achieve sub-100-micron manufacturing. Two aspects are sub-optimal using commercial laser powder bed fusion systems with infrared (… ▽ More Microscale additive manufacturing of reflective copper is becoming increasingly important for microelectronics and microcomputers, due to its excellent electrical and thermal conductivity. Yet, it remains challenging for state-of-the-art commercial metal 3D printers to achieve sub-100-micron manufacturing. Two aspects are sub-optimal using commercial laser powder bed fusion systems with infrared (IR) lasers (wavelength of 1060-1070 nm): (1) IR laser has a low absorption rate for Cu, which is energy-inefficient for manufacturing; (2) short wavelength lasers can potentially offer higher resolution processing due to the diffraction-limited processing. On the other hand, laser sintering or melting typically uses continuous wave (CW) lasers, which may reduce the manufacturing resolution due to a large heat-affected zone. Based on these facts, this study investigates the UV (wavelength of 355 nm) nanosecond (ns) laser sintering of Cu nanoparticles. Different laser processing parameters, as well as different nanoparticle packing densities, are studied. Our results show that a short-wavelength laser can reduce the required energy for sintering with decent morphology, and a densified nanoparticle powder bed favors continuous melting. We further show that sub-20 micron printing can be readily achieved with a UV ns laser. These findings provide new insights into short-wavelength laser-metal nanoparticle interactions, which may pave the way to achieve high-resolution micro and nano-scale additive manufacturing. △ Less

Submitted 28 December, 2025; v1 submitted 20 December, 2025; originally announced December 2025.

Synthetic Data Augmentation for Enhanced Chicken Carcass Instance Segmentation

Authors: Yihong Feng, Chaitanya Pallerla, Xiaomin Lin, Pouya Sohrabipour Sr, Philip Crandall, Wan Shou, Yu She, Dongyi Wang

Abstract: The poultry industry has been driven by broiler chicken production and has grown into the world's largest animal protein sector. Automated detection of chicken carcasses on processing lines is vital for quality control, food safety, and operational efficiency in slaughterhouses and poultry processing plants. However, developing robust deep learning models for tasks like instance segmentation in th… ▽ More The poultry industry has been driven by broiler chicken production and has grown into the world's largest animal protein sector. Automated detection of chicken carcasses on processing lines is vital for quality control, food safety, and operational efficiency in slaughterhouses and poultry processing plants. However, developing robust deep learning models for tasks like instance segmentation in these fast-paced industrial environments is often hampered by the need for laborious acquisition and annotation of large-scale real-world image datasets. We present the first pipeline generating photo-realistic, automatically labeled synthetic images of chicken carcasses. We also introduce a new benchmark dataset containing 300 annotated real-world images, curated specifically for poultry segmentation research. Using these datasets, this study investigates the efficacy of synthetic data and automatic data annotation to enhance the instance segmentation of chicken carcasses, particularly when real annotated data from the processing line is scarce. A small real dataset with varying proportions of synthetic images was evaluated in prominent instance segmentation models. Results show that synthetic data significantly boosts segmentation performance for chicken carcasses across all models. This research underscores the value of synthetic data augmentation as a viable and effective strategy to mitigate data scarcity, reduce manual annotation efforts, and advance the development of robust AI-driven automated detection systems for chicken carcasses in the poultry processing industry. △ Less

Submitted 24 July, 2025; originally announced July 2025.

Comments: Submitted for journal reviewing

Additive Manufacturing of Lunar Regolith for Reconfigurable Building Blocks toward Lunar Habitation

Authors: Cole McCallum, Youwen Liang, Nahid Tushar, Ben Xu, Bo Zhao, Hao Zeng, Wan Shou

Abstract: Utilizing locally available materials is a crucial step towards sustainable planetary habitation. Lunar regolith has gained tremendous interest in additive manufacturing in the past decades. However, due to the constrained manufacturing facilities and materials on the moon, many existing additive manufacturing methods are not suitable for practical on-site manufacturing. Here, we envision that lig… ▽ More Utilizing locally available materials is a crucial step towards sustainable planetary habitation. Lunar regolith has gained tremendous interest in additive manufacturing in the past decades. However, due to the constrained manufacturing facilities and materials on the moon, many existing additive manufacturing methods are not suitable for practical on-site manufacturing. Here, we envision that light-based direct sintering of lunar regolith can be a feasible approach. Instead of directly manufacturing large structures, we hypothesize that small-scale, reconfigurable building blocks can be an alternative to form large and complex structures. To verify the feasibility, we conducted laser sintering of lunar regolith simulants as a proof of concept, following a simple theoretical calculation for direct sintering using the light available in space. Different laser processing parameters are investigated to obtain controllable lunar regolith sintering. We further designed Lego-like interlocking bricks that are reconfigurable for different structure assemblies without additional material. Mechanical performance (compressive strength) of sintered cubic blocks is evaluated, showing a peak stress of ~1.5 MPa. We hope this work will inspire other in-space manufacturing techniques and enable low-cost space habitation. △ Less

Submitted 5 June, 2025; originally announced June 2025.

ChicGrasp: Imitation-Learning based Customized Dual-Jaw Gripper Control for Delicate, Irregular Bio-products Manipulation

Authors: Amirreza Davar, Zhengtong Xu, Siavash Mahmoudi, Pouya Sohrabipour, Chaitanya Pallerla, Yu She, Wan Shou, Philip Crandall, Dongyi Wang

Abstract: Automated poultry processing lines still rely on humans to lift slippery, easily bruised carcasses onto a shackle conveyor. Deformability, anatomical variance, and strict hygiene rules make conventional suction and scripted motions unreliable. We present ChicGrasp, an end--to--end hardware--software co-design for this task. An independently actuated dual-jaw pneumatic gripper clamps both chicken l… ▽ More Automated poultry processing lines still rely on humans to lift slippery, easily bruised carcasses onto a shackle conveyor. Deformability, anatomical variance, and strict hygiene rules make conventional suction and scripted motions unreliable. We present ChicGrasp, an end--to--end hardware--software co-design for this task. An independently actuated dual-jaw pneumatic gripper clamps both chicken legs, while a conditional diffusion-policy controller, trained from only 50 multi--view teleoperation demonstrations (RGB + proprioception), plans 5 DoF end--effector motion, which includes jaw commands in one shot. On individually presented raw broiler carcasses, our system achieves a 40.6\% grasp--and--lift success rate and completes the pick to shackle cycle in 38 s, whereas state--of--the--art implicit behaviour cloning (IBC) and LSTM-GMM baselines fail entirely. All CAD, code, and datasets will be open-source. ChicGrasp shows that imitation learning can bridge the gap between rigid hardware and variable bio--products, offering a reproducible benchmark and a public dataset for researchers in agricultural engineering and robot learning. △ Less

Submitted 13 May, 2025; originally announced May 2025.

Comments: Submitted for journal review

Molecular dynamics simulation of silicon nanoparticle crystallization during laser-induced forward transfer printing

Authors: Youwen Liang, Wan Shou

Abstract: Laser-induced forward transfer (LIFT) printing is a versatile technique to realize micro/nano-scale additive manufacturing of functional materials, including metals and semiconductors. However, the crystallization phenomena during LIFT printing have not been well understood, which is critical to determine the resulting microstructure and properties. In this work, we systematically investigate sili… ▽ More Laser-induced forward transfer (LIFT) printing is a versatile technique to realize micro/nano-scale additive manufacturing of functional materials, including metals and semiconductors. However, the crystallization phenomena during LIFT printing have not been well understood, which is critical to determine the resulting microstructure and properties. In this work, we systematically investigate silicon crystallization during LIFT printing using molecular dynamics (MD) simulations. Specifically, MD simulation with Stillinger-Weber (SW) potential is used to investigate the size effect and surface influence on the crystallization of Si nanoparticles during transportation in air. We found that with a decrease in nanoparticle size, crystallization becomes increasingly rare, even at low cooling rates. The nucleation location of different particles is also analyzed and almost always starts at a sub-surface location (below 5 Å). The evolution of the atomic structure during solidification is also monitored to guide LIFT printing of Si. Our simulation results indicate that nano-confinement induced by the surface layer can lead to single-crystal structure formation, which may shed light on additive manufacturing of single-crystal structures and devices. △ Less

Submitted 2 February, 2026; v1 submitted 5 April, 2025; originally announced April 2025.

Feedback Regulated Opto-Mechanical Soft Robotic Actuators

Authors: Jianfeng Yang, Haotian Pi, Zixuan Deng, Hongshuang Guo, Wan Shou, Hang Zhang, Hao Zeng

Abstract: Natural organisms can convert environmental stimuli into sensory feedback to regulate their body and realize active adaptivity. However, realizing such a feedback-regulation mechanism in synthetic material systems remains a grand challenge. It is believed that achieving complex feedback mechanisms in responsive materials will pave the way toward autonomous, intelligent structure and actuation with… ▽ More Natural organisms can convert environmental stimuli into sensory feedback to regulate their body and realize active adaptivity. However, realizing such a feedback-regulation mechanism in synthetic material systems remains a grand challenge. It is believed that achieving complex feedback mechanisms in responsive materials will pave the way toward autonomous, intelligent structure and actuation without complex electronics. Inspired by living systems, we report a general principle to design and construct such feedback loops in light-responsive materials. Specifically, we design a baffle-actuator mechanism to incorporate programmed feedback into the opto-mechanical responsiveness. By simply addressing the baffle position with respect to the incident light beam, positive and negative feedback are programmed. We demonstrate the transformation of a light-bending strip into a switcher, where the intensity of light determines the energy barrier under positive feedback, realizing multi-stable shape-morphing. By leveraging the negative feedback and associated homeostasis, we demonstrate two soft robots, i.e., a locomotor and a swimmer. Furthermore, we unveil the ubiquity of feedback in light-responsive materials, which provides new insight into self-regulated robotic matters. △ Less

Submitted 20 December, 2024; originally announced December 2024.

UniT: Data Efficient Tactile Representation with Generalization to Unseen Objects

Authors: Zhengtong Xu, Raghava Uppuluri, Xinwei Zhang, Cael Fitch, Philip Glen Crandall, Wan Shou, Dongyi Wang, Yu She

Abstract: UniT is an approach to tactile representation learning, using VQGAN to learn a compact latent space and serve as the tactile representation. It uses tactile images obtained from a single simple object to train the representation with generalizability. This tactile representation can be zero-shot transferred to various downstream tasks, including perception tasks and manipulation policy learning. O… ▽ More UniT is an approach to tactile representation learning, using VQGAN to learn a compact latent space and serve as the tactile representation. It uses tactile images obtained from a single simple object to train the representation with generalizability. This tactile representation can be zero-shot transferred to various downstream tasks, including perception tasks and manipulation policy learning. Our benchmarkings on in-hand 3D pose and 6D pose estimation tasks and a tactile classification task show that UniT outperforms existing visual and tactile representation learning methods. Additionally, UniT's effectiveness in policy learning is demonstrated across three real-world tasks involving diverse manipulated objects and complex robot-object-environment interactions. Through extensive experimentation, UniT is shown to be a simple-to-train, plug-and-play, yet widely effective method for tactile representation learning. For more details, please refer to our open-source repository https://github.com/ZhengtongXu/UniT and the project website https://zhengtongxu.github.io/unit-website/. △ Less

Submitted 1 April, 2025; v1 submitted 12 August, 2024; originally announced August 2024.

Robot Tape Manipulation for 3D Printing

Authors: Nahid Tushar, Rencheng Wu, Yu She, Wenchao Zhou, Wan Shou

Abstract: 3D printing has enabled various applications using different forms of materials, such as filaments, sheets, and inks. Typically, during 3D printing, feedstocks are transformed into discrete building blocks and placed or deposited in a designated location similar to the manipulation and assembly of discrete objects. However, 3D printing of continuous and flexible tape (with the geometry between fil… ▽ More 3D printing has enabled various applications using different forms of materials, such as filaments, sheets, and inks. Typically, during 3D printing, feedstocks are transformed into discrete building blocks and placed or deposited in a designated location similar to the manipulation and assembly of discrete objects. However, 3D printing of continuous and flexible tape (with the geometry between filaments and sheets) without breaking or transformation remains underexplored and challenging. Here, we report the design and implementation of a customized end-effector, i.e., tape print module (TPM), to realize robot tape manipulation for 3D printing by leveraging the tension formed on the tape between two endpoints. We showcase the feasibility of manufacturing representative 2D and 3D structures while utilizing conductive copper tape for various electronic applications, such as circuits and sensors. We believe this manipulation strategy could unlock the potential of other tape materials for manufacturing, including packaging tape and carbon fiber prepreg tape, and inspire new mechanisms for robot manipulation, 3D printing, and packaging. △ Less

Submitted 17 January, 2024; originally announced January 2024.

Computational Discovery of Microstructured Composites with Optimal Stiffness-Toughness Trade-Offs

Authors: Beichen Li, Bolei Deng, Wan Shou, Tae-Hyun Oh, Yuanming Hu, Yiyue Luo, Liang Shi, Wojciech Matusik

Abstract: The conflict between stiffness and toughness is a fundamental problem in engineering materials design. However, the systematic discovery of microstructured composites with optimal stiffness-toughness trade-offs has never been demonstrated, hindered by the discrepancies between simulation and reality and the lack of data-efficient exploration of the entire Pareto front. We introduce a generalizable… ▽ More The conflict between stiffness and toughness is a fundamental problem in engineering materials design. However, the systematic discovery of microstructured composites with optimal stiffness-toughness trade-offs has never been demonstrated, hindered by the discrepancies between simulation and reality and the lack of data-efficient exploration of the entire Pareto front. We introduce a generalizable pipeline that integrates physical experiments, numerical simulations, and artificial neural networks to address both challenges. Without any prescribed expert knowledge of material design, our approach implements a nested-loop proposal-validation workflow to bridge the simulation-to-reality gap and discover microstructured composites that are stiff and tough with high sample efficiency. Further analysis of Pareto-optimal designs allows us to automatically identify existing toughness enhancement mechanisms, which were previously discovered through trial-and-error or biomimicry. On a broader scale, our method provides a blueprint for computational design in various research areas beyond solid mechanics, such as polymer chemistry, fluid dynamics, meteorology, and robotics. △ Less

Submitted 3 January, 2024; v1 submitted 31 January, 2023; originally announced February 2023.

Designing Composites with Target Effective Young's Modulus using Reinforcement Learning

Authors: Aldair E. Gongora, Siddharth Mysore, Beichen Li, Wan Shou, Wojciech Matusik, Elise F. Morgan, Keith A. Brown, Emily Whiting

Abstract: Advancements in additive manufacturing have enabled design and fabrication of materials and structures not previously realizable. In particular, the design space of composite materials and structures has vastly expanded, and the resulting size and complexity has challenged traditional design methodologies, such as brute force exploration and one factor at a time (OFAT) exploration, to find optimum… ▽ More Advancements in additive manufacturing have enabled design and fabrication of materials and structures not previously realizable. In particular, the design space of composite materials and structures has vastly expanded, and the resulting size and complexity has challenged traditional design methodologies, such as brute force exploration and one factor at a time (OFAT) exploration, to find optimum or tailored designs. To address this challenge, supervised machine learning approaches have emerged to model the design space using curated training data; however, the selection of the training data is often determined by the user. In this work, we develop and utilize a Reinforcement learning (RL)-based framework for the design of composite structures which avoids the need for user-selected training data. For a 5 $\times$ 5 composite design space comprised of soft and compliant blocks of constituent material, we find that using this approach, the model can be trained using 2.78% of the total design space consists of $2^{25}$ design possibilities. Additionally, the developed RL-based framework is capable of finding designs at a success rate exceeding 90%. The success of this approach motivates future learning frameworks to utilize RL for the design of composites and other material systems. △ Less

Submitted 7 October, 2021; originally announced October 2021.

Comments: Accepted to the Symposium on Computational Fabrication (SCF) 2021

Dynamic Modeling of Hand-Object Interactions via Tactile Sensing

Authors: Qiang Zhang, Yunzhu Li, Yiyue Luo, Wan Shou, Michael Foshey, Junchi Yan, Joshua B. Tenenbaum, Wojciech Matusik, Antonio Torralba

Abstract: Tactile sensing is critical for humans to perform everyday tasks. While significant progress has been made in analyzing object grasping from vision, it remains unclear how we can utilize tactile sensing to reason about and model the dynamics of hand-object interactions. In this work, we employ a high-resolution tactile glove to perform four different interactive activities on a diversified set of… ▽ More Tactile sensing is critical for humans to perform everyday tasks. While significant progress has been made in analyzing object grasping from vision, it remains unclear how we can utilize tactile sensing to reason about and model the dynamics of hand-object interactions. In this work, we employ a high-resolution tactile glove to perform four different interactive activities on a diversified set of objects. We build our model on a cross-modal learning framework and generate the labels using a visual processing pipeline to supervise the tactile model, which can then be used on its own during the test time. The tactile model aims to predict the 3d locations of both the hand and the object purely from the touch data by combining a predictive model and a contrastive learning module. This framework can reason about the interaction patterns from the tactile data, hallucinate the changes in the environment, estimate the uncertainty of the prediction, and generalize to unseen objects. We also provide detailed ablation studies regarding different system designs as well as visualizations of the predicted trajectories. This work takes a step on dynamics modeling in hand-object interactions from dense tactile sensing, which opens the door for future applications in activity learning, human-computer interactions, and imitation learning for robotics. △ Less

Submitted 9 September, 2021; originally announced September 2021.

Comments: IROS 2021. First two authors contributed equally. Project page: http://phystouch.csail.mit.edu/

Accelerated Discovery of 3D Printing Materials Using Data-Driven Multi-Objective Optimization

Authors: Timothy Erps, Michael Foshey, Mina Konaković Luković, Wan Shou, Hanns Hagen Goetzke, Herve Dietsch, Klaus Stoll, Bernhard von Vacano, Wojciech Matusik

Abstract: Additive manufacturing has become one of the forefront technologies in fabrication, enabling new products impossible to manufacture before. Although many materials exist for additive manufacturing, they typically suffer from performance trade-offs preventing them from replacing traditional manufacturing techniques. Current materials are designed with inefficient human-driven intuition-based method… ▽ More Additive manufacturing has become one of the forefront technologies in fabrication, enabling new products impossible to manufacture before. Although many materials exist for additive manufacturing, they typically suffer from performance trade-offs preventing them from replacing traditional manufacturing techniques. Current materials are designed with inefficient human-driven intuition-based methods, leaving them short of optimal solutions. We propose a machine learning approach to accelerate the discovery of additive manufacturing materials with optimal trade-offs in mechanical performance. A multi-objective optimization algorithm automatically guides the experimental design by proposing how to mix primary formulations to create better-performing materials. The algorithm is coupled with a semi-autonomous fabrication platform to significantly reduce the number of performed experiments and overall time to solution. Without any prior knowledge of the primary formulations, the proposed methodology autonomously uncovers twelve optimal composite formulations and enlarges the discovered performance space 288 times after only 30 experimental iterations. This methodology could easily be generalized to other material formulation problems and enable completely automated discovery of a wide variety of material designs. △ Less

Submitted 29 June, 2021; originally announced June 2021.

Polygrammar: Grammar for Digital Polymer Representation and Generation

Authors: Minghao Guo, Wan Shou, Liane Makatura, Timothy Erps, Michael Foshey, Wojciech Matusik

Abstract: Polymers are widely-studied materials with diverse properties and applications determined by different molecular structures. It is essential to represent these structures clearly and explore the full space of achievable chemical designs. However, existing approaches are unable to offer comprehensive design models for polymers because of their inherent scale and structural complexity. Here, we pres… ▽ More Polymers are widely-studied materials with diverse properties and applications determined by different molecular structures. It is essential to represent these structures clearly and explore the full space of achievable chemical designs. However, existing approaches are unable to offer comprehensive design models for polymers because of their inherent scale and structural complexity. Here, we present a parametric, context-sensitive grammar designed specifically for the representation and generation of polymers. As a demonstrative example, we implement our grammar for polyurethanes. Using our symbolic hypergraph representation and 14 simple production rules, our PolyGrammar is able to represent and generate all valid polyurethane structures. We also present an algorithm to translate any polyurethane structure from the popular SMILES string format into our PolyGrammar representation. We test the representative power of PolyGrammar by translating a dataset of over 600 polyurethane samples collected from literature. Furthermore, we show that PolyGrammar can be easily extended to the other copolymers and homopolymers such as polyacrylates. By offering a complete, explicit representation scheme and an explainable generative model with validity guarantees, our PolyGrammar takes an important step toward a more comprehensive and practical system for polymer discovery and exploration. As the first bridge between formal languages and chemistry, PolyGrammar also serves as a critical blueprint to inform the design of similar grammars for other chemistries, including organic and inorganic molecules. △ Less

Submitted 5 May, 2021; originally announced May 2021.

Phase-change silicon as an ultrafast active photonic platform

Authors: Letian Wang, Matthew Eliceiri, Yang Deng, Yoonsoo Rho, Wan Shou, Heng Pan, Jie Yao, Costas P. Grigoropoulos

Abstract: Phase change material (PCM) features distinct optical or electronic properties between amorphous and crystalline states. Recently, it starts to play a key role in the emerging photonic applications like optoelectronic display, dynamic wavefront control, on-chip photonic memory and computation. However, current PCMs do not refract effectively at visible wavelengths and suffer from deformation and d… ▽ More Phase change material (PCM) features distinct optical or electronic properties between amorphous and crystalline states. Recently, it starts to play a key role in the emerging photonic applications like optoelectronic display, dynamic wavefront control, on-chip photonic memory and computation. However, current PCMs do not refract effectively at visible wavelengths and suffer from deformation and decomposition, limiting the repeatability and vast visible wavelength applications. Silicon as the fundamental material for electronics and photonics, has never been considered as phase change material, due to its ultrafast crystallization kinetics. Here we show the striking fact that nanoscale silicon domains can be reversibly crystallized and amorphized under nanosecond laser pulses. For a typical disk resonator, it also provides a 25% non-volatile modulation at nanosecond time scale. We further show proof-of-concept experiments that such attributes could enable ultra-high resolution dielectric color display and dynamic visible wavefront control. △ Less

Submitted 26 April, 2019; originally announced April 2019.