College+of+Engineering
-
KAIST debuts “DreamWaQer” - a quadrupedal robot that can walk in the dark
- The team led by Professor Hyun Myung of the School of Electrical Engineering developed “DreamWaQ”, a deep reinforcement learning-based walking robot control technology that can walk in an atypical environment without visual and/or tactile information
- Utilization of “DreamWaQ” technology can enable mass production of various types of “DreamWaQers”
- Expected to be used in exploration of atypical environment involving unique circumstances such as disasters by fire.
A team of Korean engineering researchers has developed a quadrupedal robot technology that can climb up and down the steps and moves without falling over in uneven environments such as tree roots without the help of visual or tactile sensors even in disastrous situations in which visual confirmation is impeded due to darkness or thick smoke from the flames.
KAIST (President Kwang Hyung Lee) announced on the 29th of March that Professor Hyun Myung's research team at the Urban Robotics Lab in the School of Electrical Engineering developed a walking robot control technology that enables robust 'blind locomotion' in various atypical environments.
< (From left) Prof. Hyun Myung, Doctoral Candidates I Made Aswin Nahrendra, Byeongho Yu, and Minho Oh. In the foreground is the DreamWaQer, a quadrupedal robot equipped with DreamWaQ technology. >
The KAIST research team developed "DreamWaQ" technology, which was named so as it enables walking robots to move about even in the dark, just as a person can walk without visual help fresh out of bed and going to the bathroom in the dark. With this technology installed atop any legged robots, it will be possible to create various types of "DreamWaQers".
Existing walking robot controllers are based on kinematics and/or dynamics models. This is expressed as a model-based control method. In particular, on atypical environments like the open, uneven fields, it is necessary to obtain the feature information of the terrain more quickly in order to maintain stability as it walks. However, it has been shown to depend heavily on the cognitive ability to survey the surrounding environment.
In contrast, the controller developed by Professor Hyun Myung's research team based on deep reinforcement learning (RL) methods can quickly calculate appropriate control commands for each motor of the walking robot through data of various environments obtained from the simulator. Whereas the existing controllers that learned from simulations required a separate re-orchestration to make it work with an actual robot, this controller developed by the research team is expected to be easily applied to various walking robots because it does not require an additional tuning process.
DreamWaQ, the controller developed by the research team, is largely composed of a context estimation network that estimates the ground and robot information and a policy network that computes control commands. The context-aided estimator network estimates the ground information implicitly and the robot’s status explicitly through inertial information and joint information. This information is fed into the policy network to be used to generate optimal control commands. Both networks are learned together in the simulation.
While the context-aided estimator network is learned through supervised learning, the policy network is learned through an actor-critic architecture, a deep RL methodology. The actor network can only implicitly infer surrounding terrain information. In the simulation, the surrounding terrain information is known, and the critic, or the value network, that has the exact terrain information evaluates the policy of the actor network.
This whole learning process takes only about an hour in a GPU-enabled PC, and the actual robot is equipped with only the network of learned actors. Without looking at the surrounding terrain, it goes through the process of imagining which environment is similar to one of the various environments learned in the simulation using only the inertial sensor (IMU) inside the robot and the measurement of joint angles. If it suddenly encounters an offset, such as a staircase, it will not know until its foot touches the step, but it will quickly draw up terrain information the moment its foot touches the surface. Then the control command suitable for the estimated terrain information is transmitted to each motor, enabling rapidly adapted walking.
The DreamWaQer robot walked not only in the laboratory environment, but also in an outdoor environment around the campus with many curbs and speed bumps, and over a field with many tree roots and gravel, demonstrating its abilities by overcoming a staircase with a difference of a height that is two-thirds of its body. In addition, regardless of the environment, the research team confirmed that it was capable of stable walking ranging from a slow speed of 0.3 m/s to a rather fast speed of 1.0 m/s.
The results of this study were produced by a student in doctorate course, I Made Aswin Nahrendra, as the first author, and his colleague Byeongho Yu as a co-author. It has been accepted to be presented at the upcoming IEEE International Conference on Robotics and Automation (ICRA) scheduled to be held in London at the end of May. (Paper title: DreamWaQ: Learning Robust Quadrupedal Locomotion With Implicit Terrain Imagination via Deep Reinforcement Learning)
The videos of the walking robot DreamWaQer equipped with the developed DreamWaQ can be found at the address below.
Main Introduction: https://youtu.be/JC1_bnTxPiQ Experiment Sketches: https://youtu.be/mhUUZVbeDA0
Meanwhile, this research was carried out with the support from the Robot Industry Core Technology Development Program of the Ministry of Trade, Industry and Energy (MOTIE). (Task title: Development of Mobile Intelligence SW for Autonomous Navigation of Legged Robots in Dynamic and Atypical Environments for Real Application)
< Figure 1. Overview of DreamWaQ, a controller developed by this research team. This network consists of an estimator network that learns implicit and explicit estimates together, a policy network that acts as a controller, and a value network that provides guides to the policies during training. When implemented in a real robot, only the estimator and policy network are used. Both networks run in less than 1 ms on the robot's on-board computer. >
< Figure 2. Since the estimator can implicitly estimate the ground information as the foot touches the surface, it is possible to adapt quickly to rapidly changing ground conditions. >
< Figure 3. Results showing that even a small walking robot was able to overcome steps with height differences of about 20cm. >
2023.05.18 View 6518 -
Synthetic sRNAs to knockdown genes in medical and industrial bacteria
Bacteria are intimately involved in our daily lives. These microorganisms have been used in human history for food such as cheese, yogurt, and wine, In more recent years, through metabolic engineering, microorganisms been used extensively as microbial cell factories to manufacture plastics, feed for livestock, dietary supplements, and drugs. However, in addition to these bacteria that are beneficial to human lives, pathogens such as Pneumonia, Salmonella, and Staphylococcus that cause various infectious diseases are also ubiquitously present. It is important to be able to metabolically control these beneficial industrial bacteria for high value-added chemicals production and to manipulate harmful pathogens to suppress its pathogenic traits.
KAIST (President Kwang Hyung Lee) announced on the 10th that a research team led by Distinguished Professor Sang Yup Lee of the Department of Biochemical Engineering has developed a new sRNA tool that can effectively inhibit target genes in various bacteria, including both Gram-negative and Gram-positive bacteria. The research results were published online on April 24 in Nature Communications.
※ Thesis title: Targeted and high-throughput gene knockdown in diverse bacteria using synthetic sRNAs
※ Author information : Jae Sung Cho (co-1st), Dongsoo Yang (co-1st), Cindy Pricilia Surya Prabowo (co-author), Mohammad Rifqi Ghiffary (co-author), Taehee Han (co-author), Kyeong Rok Choi (co-author), Cheon Woo Moon (co-author), Hengrui Zhou (co-author), Jae Yong Ryu (co-author), Hyun Uk Kim (co-author) and Sang Yup Lee (corresponding author).
sRNA is an effective tool for synthesizing and regulating target genes in E. coli, but it has been difficult to apply to industrially useful Gram-positive bacteria such as Bacillus subtilis and Corynebacterium in addition to Gram-negative bacteria such as E. coli.
To address this issue, a research team led by Distinguished Professor Lee Sang Yup Lee of the Department of Chemical and Biomolecular Engineering at KAIST developed a new sRNA platform that can effectively suppress target genes in various bacteria, including both Gram-negative and positive bacteria. The research team surveyed thousands of microbial-derived sRNA systems in the microbial database, and eventually designated the sRNA system derived from 'Bacillus subtilis' that showed the highest gene knockdown efficiency, and designated it as “Broad-Host-Range sRNA”, or BHR-sRNA.
A similar well-known system is the CRISPR interference (CRISPRi) system, which is a modified CRISPR system that knocks down gene expression by suppressing the gene transcription process. However, the Cas9 protein in the CRISPRi system has a very high molecular weight, and there have been reports growth inhibition in bacteria. The BHR-sRNA system developed in this study did not affect bacterial growth while showing similar gene knockdown efficiencies to CRISPRi.
< Figure 1. a) Schematic illustration demonstrating the mechanism of syntetic sRNA b) Phylogenetic tree of the 16 Gram-negative and Gram-positive bacterial species tested for gene knockdown by the BHR-sRNA system. >
To validate the versatility of the BHR-sRNA system, 16 different gram-negative and gram-positive bacteria were selected and tested, where the BHR-sRNA system worked successfully in 15 of them. In addition, it was demonstrated that the gene knockdown capability was more effective than that of the existing E. coli-based sRNA system in 10 bacteria. The BHR-sRNA system proved to be a universal tool capable of effectively inhibiting gene expression in various bacteria.
In order to address the problem of antibiotic-resistant pathogens that have recently become more serious, the BHR-sRNA was demonstrated to suppress the pathogenicity by suppressing the gene producing the virulence factor. By using BHR-sRNA, biofilm formation, one of the factors resulting in antibiotic resistance, was inhibited by 73% in Staphylococcus epidermidis a pathogen that can cause hospital-acquired infections. Antibiotic resistance was also weakened by 58% in the pneumonia causing bacteria Klebsiella pneumoniae. In addition, BHR-sRNA was applied to industrial bacteria to develop microbial cell factories to produce high value-added chemicals with better production performance. Notably, superior industrial strains were constructed with the aid of BHR-sRNA to produce the following chemicals: valerolactam, a raw material for polyamide polymers, methyl-anthranilate, a grape-flavor food additive, and indigoidine, a blue-toned natural dye.
The BHR-sRNA developed through this study will help expedite the commercialization of bioprocesses to produce high value-added compounds and materials such as artificial meat, jet fuel, health supplements, pharmaceuticals, and plastics. It is also anticipated that to help eradicating antibiotic-resistant pathogens in preparation for another upcoming pandemic. “In the past, we could only develop new tools for gene knockdown for each bacterium, but now we have developed a tool that works for a variety of bacteria” said Distinguished Professor Sang Yup Lee.
This work was supported by the Development of Next-generation Biorefinery Platform Technologies for Leading Bio-based Chemicals Industry Project and the Development of Platform Technologies of Microbial Cell Factories for the Next-generation Biorefineries Project from NRF supported by the Korean MSIT.
2023.05.10 View 4889 -
Seanie Lee of KAIST Kim Jaechul Graduate School of AI, named the 2023 Apple Scholars in AI Machine Learning
Seanie Lee, a Ph.D. candidate at the Kim Jaechul Graduate School of AI, has been selected as one of the Apple Scholars in AI/ML PhD fellowship program recipients for 2023. Lee, advised by Sung Ju Hwang and Juho Lee, is a rising star in AI.
< Seanie Lee of KAIST Kim Jaechul Graduate School of AI >
The Apple Scholars in AI/ML PhD fellowship program, launched in 2020, aims to discover and support young researchers with a promising future in computer science. Each year, a handful of graduate students in related fields worldwide are selected for the program. For the following two years, the selected students are provided with financial support for research, international conference attendance, internship opportunities, and mentorship by an Apple engineer.
This year, 22 PhD students were selected from leading universities worldwide, including Johns Hopkins University, MIT, Stanford University, Imperial College London, Edinburgh University, Tsinghua University, HKUST, and Technion. Seanie Lee is the first Korean student to be selected for the program.
Lee’s research focuses on transfer learning, a subfield of AI that reuses pre-trained AI models on large datasets such as images or text corpora to train them for new purposes.
(*text corpus: a collection of text resources in computer-readable forms)
His work aims to improve the performance of transfer learning by developing new data augmentation methods that allow for more effective training using few training data samples and new regularization techniques that prevent the overfitting of large AI models to training data. He has published 11 papers, all of which were accepted to top-tier conferences such as the Annual Meeting of the Association for Computational Linguistics (ACL), International Conference on Learning Representations (ICLR), and Annual Conference on Neural Information Processing Systems (NeurIPS).
“Being selected as one of the Apple Scholars in AI/ML PhD fellowship program is a great motivation for me,” said Lee. “So far, AI research has been largely focused on computer vision and natural language processing, but I want to push the boundaries now and use modern tools of AI to solve problems in natural science, like physics.”
2023.04.20 View 4590 -
KAIST Team Develops Highly-Sensitive Wearable Piezoelectric Blood Pressure Sensor for Continuous Health Monitoring
- A collaborative research team led by KAIST Professor Keon Jae Lee verifies the accuracy of the highly-sensitive sensor through clinical trials
- Commercialization of the watch and patch-type sensor is in progress
A KAIST research team led by Professor Keon Jae Lee from the Department of Materials Science and Engineering and the College of Medicine of the Catholic University of Korea has developed a highly sensitive, wearable piezoelectric blood pressure sensor.
Blood pressure is a critical indicator for assessing general health and predicting stroke or heart failure. In particular, cardiovascular disease is the leading cause of global death, therefore, periodic measurement of blood pressure is crucial for personal healthcare.
Recently, there has been a growing interest in healthcare devices for continuous blood pressure monitoring. Although smart watches using LED-based photoplethysmography (PPG) technology have been on market, these devices have been limited by the accuracy constraints of optical sensors, making it hard to meet the international standards of automatic sphygmomanometers.
Professor Lee’s team has developed the wearable piezoelectric blood pressure sensor by transferring a highly sensitive, inorganic piezoelectric membrane from bulk sapphire substrates to flexible substrates. Ultrathin piezoelectric sensors with a thickness of several micrometers (one hundredth of the human hair) exhibit conformal contact with the skin to successfully collect accurate blood pressure from the subtle pulsation of the blood vessels.
Clinical trial at the St. Mary’s Hospital of the Catholic University validated the accuracy of blood pressure sensor at par with international standard with errors within ±5 mmHg and a standard deviation under 8 mmHg for both systolic and diastolic blood pressure. In addition, the research team successfully embedded the sensor on a watch-type product to enable continuous monitoring of blood pressure.
Prof. Keon Jae Lee said, “Major target of our healthcare devices is hypertensive patients for their daily medical check-up. We plan to develop a comfortable patch-type sensor to monitor blood pressure during sleep and have a start-up company commercialize these watch and patch-type products soon.”
This result titled “Clinical validation of wearable piezoelectric blood pressure sensor for health monitoring” was published in the online issue of Advanced Materials on March 24th, 2023. (DOI: 10.1002/adma.202301627)
Figure 1. Schematic illustration of the overall concept for a wearable piezoelectric blood pressure sensor (WPBPS).
Figure 2. Wearable piezoelectric blood pressure sensor (WPBPS) mounted on a watch (a) Schematic design of the WPBPS-embedded wristwatch. (b) Block diagram of the wireless communication circuit, which filters, amplifies, and transmits wireless data to portable devices. (c) Pulse waveforms transmitted from the wristwatch to the portable device by the wireless communication circuit. The inset shows a photograph of monitoring a user’s beat-to-beat pulses and their corresponding BP values in real time using the developed WPBPS-mounted wristwatch.
2023.04.17 View 5138 -
A biohybrid system to extract 20 times more bioplastic from CO2 developed by KAIST researchers
As the issues surrounding global climate change intensify, more attention and determined efforts are required to re-grasp the issue as a state of “crisis” and respond to it properly. Among the various methods of recycling CO2, the electrochemical CO2 conversion technology is a technology that can convert CO2 into useful chemical substances using electrical energy. Since it is easy to operate facilities and can use the electricity from renewable sources like the solar cells or the wind power, it has received a lot of attention as an eco-friendly technology can contribute to reducing greenhouse gases and achieve carbon neutrality.
KAIST (President Kwang Hyung Lee) announced on the 30th that the joint research team led by Professor Hyunjoo Lee and Distinguished Professor Sang Yup Lee of the Department of Chemical and Biomolecular Engineering succeeded in developing a technology that produces bioplastics from CO2 with high efficiency by developing a hybrid system that interlinked the electrochemical CO2 conversion and microbial bio conversion methods together. The results of the research, which showed the world's highest productivity by more than 20 times compared to similar systems, were published online on March 27th in the "Proceedings of the National Academy of Sciences (PNAS)".
※ Paper title: Biohybrid CO2 electrolysis for the direct synthesis of polyesters from CO2
※ Author information: Jinkyu Lim (currently at Stanford Linear Accelerator Center, co-first author), So Young Choi (KAIST, co-first author), Jae Won Lee (KAIST, co-first author), Hyunjoo Lee (KAIST, corresponding author), Sang Yup Lee (KAIST, corresponding author)
For the efficient conversion of CO2, high-efficiency electrode catalysts and systems are actively being developed. As conversion products, only compounds containing one or up to three carbon atoms are produced on a limited basis. Compounds of one carbon, such as CO, formic acid, and ethylene, are produced with relatively high efficiency. Liquid compounds of several carbons, such as ethanol, acetic acid, and propanol, can also be produced by these systems, but due to the nature of the chemical reaction that requires more electrons, there are limitations involving the conversion efficiency and the product selection.
Accordingly, a joint research team led by Professor Hyunjoo Lee and Distinguished Professor Sang Yup Lee of the Department of Chemical and Biomolecular Engineering at KAIST developed a technology to produce bioplastics from CO2 by linking electrochemical conversion technology with bioconversion method that uses microorganisms.
This electrochemical-bio hybrid system is in the form of having an electrolyzer, in which electrochemical conversion reactions occur, connected to a fermenter, in which microorganisms are cultured. When CO2 is converted to formic acid in the electrolyzer, and it is fed into the fermenter in which the microbes like the Cupriavidus necator, in this case, consumes the carbon source to produce polyhydroxyalkanoate (PHA), a microbial-derived bioplastic.
According to the research results of the existing hybrid concepts, there was a disadvantage of having low productivity or stopping at a non-continuous process due to problems of low efficiency of the electrolysis and irregular results arising from the culturing conditions of the microbes.
In order to overcome these problems, the joint research team made formic acid with a gas diffusion electrode using gaseous CO2. In addition, the team developed a 'physiologically compatible catholyte' that can be used as a culture medium for microorganisms as well as an electrolyte that allows the electrolysis to occur sufficiently without inhibiting the growth of microorganisms, without having to have a additional separation and purification process, which allowed the acide to be supplied directly to microorganisms.
Through this, the electrolyte solution containing formic acid made from CO2 enters the fermentation tank, is used for microbial culture, and enters the electrolyzer to be circulated, maximizing the utilization of the electrolyte solution and remaining formic acid. In addition, a filter was installed to ensure that only the electrolyte solution with any and all microorganisms that can affect the electrosis filtered out is supplied back to the electrolyzer, and that the microorganisms exist only in the fermenter, designing the two system to work well together with utmost efficiency.
Through the developed hybrid system, the produced bioplastic, poly-3-hydroxybutyrate (PHB), of up to 83% of the cell dry weight was produced from CO2, which produced 1.38g of PHB from a 4 cm2 electrode, which is the world's first gram(g) level production and is more than 20 times more productive than previous research. In addition, the hybrid system is expected to be applied to various industrial processes in the future as it shows promises of the continuous culture system.
The corresponding authors, Professor Hyunjoo Lee and Distinguished Professor Sang Yup Lee noted that “The results of this research are technologies that can be applied to the production of various chemical substances as well as bioplastics, and are expected to be used as key parts needed in achieving carbon neutrality in the future.”
This research was received and performed with the supports from the CO2 Reduction Catalyst and Energy Device Technology Development Project, the Heterogeneous Atomic Catalyst Control Project, and the Next-generation Biorefinery Source Technology Development Project to lead the Biochemical Industry of the Oil-replacement Eco-friendly Chemical Technology Development Program by the Ministry of Science and ICT.
Figure 1. Schematic diagram and photo of the biohybrid CO2 electrolysis system.
(A) A conceptual scheme and (B) a photograph of the biohybrid CO2 electrolysis system. (C) A detailed scheme of reaction inside the system. Gaseous CO2 was converted to formate in the electrolyzer, and the formate was converted to PHB by the cells in the fermenter. The catholyte was developed so that it is compatible with both CO2 electrolysis and fermentation and was continuously circulated.
2023.03.30 View 6541 -
KAIST researchers devises a technology to utilize ultrahigh-resolution micro-LED with 40% reduced self-generated heat
In the digitized modern life, various forms of future displays, such as wearable and rollable displays are required. More and more people are wanting to connect to the virtual world whenever and wherever with the use of their smartglasses or smartwatches. Even further, we’ve been hearing about medical diagnosis kit on a shirt and a theatre-hat. However, it is not quite here in our hands yet due to technical limitations of being unable to fit as many pixels as a limited surface area of a glasses while keeping the power consumption at the a level that a hand held battery can supply, all the while the resolution of 4K+ is needed in order to perfectly immerse the users into the augmented or virtual reality through a wireless smartglasses or whatever the device.
KAIST (President Kwang Hyung Lee) announced on the 22nd that Professor Sang Hyeon Kim's research team of the Department of Electrical and Electronic Engineering re-examined the phenomenon of efficiency degradation of micro-LEDs with pixels in a size of micrometers (μm, one millionth of a meter) and found that it was possible to fundamentally resolve the problem by the use of epitaxial structure engineering.
Epitaxy refers to the process of stacking gallium nitride crystals that are used as a light emitting body on top of an ultrapure silicon or sapphire substrate used for μLEDs as a medium.
μLED is being actively studied because it has the advantages of superior brightness, contrast ratio, and lifespan compared to OLED. In 2018, Samsung Electronics commercialized a product equipped with μLED called 'The Wall'. And there is a prospect that Apple may be launching a μLED-mounted product in 2025.
In order to manufacture μLEDs, pixels are formed by cutting the epitaxial structure grown on a wafer into a cylinder or cuboid shape through an etching process, and this etching process is accompanied by a plasma-based process. However, these plasmas generate defects on the side of the pixel during the pixel formation process.
Therefore, as the pixel size becomes smaller and the resolution increases, the ratio of the surface area to the volume of the pixel increases, and defects on the side of the device that occur during processing further reduce the device efficiency of the μLED. Accordingly, a considerable amount of research has been conducted on mitigating or removing sidewall defects, but this method has a limit to the degree of improvement as it must be done at the post-processing stage after the grown of the epitaxial structure is finished.
The research team identified that there is a difference in the current moving to the sidewall of the μLED depending on the epitaxial structure during μLED device operation, and based on the findings, the team built a structure that is not sensitive to sidewall defects to solve the problem of reduced efficiency due to miniaturization of μLED devices. In addition, the proposed structure reduced the self-generated heat while the device was running by about 40% compared to the existing structure, which is also of great significance in commercialization of ultrahigh-resolution μLED displays.
This study, which was led by Woo Jin Baek of Professor Sang Hyeon Kim's research team at the KAIST School of Electrical and Electronic Engineering as the first author with guidance by Professor Sang Hyeon Kim and Professor Dae-Myeong Geum of the Chungbuk National University (who was with the team as a postdoctoral researcher at the time) as corresponding authors, was published in the international journal, 'Nature Communications' on March 17th. (Title of the paper: Ultra-low-current driven InGaN blue micro light-emitting diodes for electrically efficient and self-heating relaxed microdisplay).
Professor Sang Hyeon Kim said, "This technological development has great meaning in identifying the cause of the drop in efficiency, which was an obstacle to miniaturization of μLED, and solving it with the design of the epitaxial structure.“ He added, ”We are looking forward to it being used in manufacturing of ultrahigh-resolution displays in the future."
This research was carried out with the support of the Samsung Future Technology Incubation Center.
Figure 1. Image of electroluminescence distribution of μLEDs fabricated from epitaxial structures with quantum barriers of different thicknesses while the current is running
Figure 2. Thermal distribution images of devices fabricated with different epitaxial structures under the same amount of light.
Figure 3. Normalized external quantum efficiency of the device fabricated with the optimized epitaxial structure by sizes.
2023.03.23 View 4348 -
KAIST leads AI-based analysis on drug-drug interactions involving Paxlovid
KAIST (President Kwang Hyung Lee) announced on the 16th that an advanced AI-based drug interaction prediction technology developed by the Distinguished Professor Sang Yup Lee's research team in the Department of Biochemical Engineering that analyzed the interaction between the PaxlovidTM ingredients that are used as COVID-19 treatment and other prescription drugs was published as a thesis. This paper was published in the online edition of 「Proceedings of the National Academy of Sciences of America」 (PNAS), an internationally renowned academic journal, on the 13th of March.
* Thesis Title: Computational prediction of interactions between Paxlovid and prescription drugs (Authored by Yeji Kim (KAIST, co-first author), Jae Yong Ryu (Duksung Women's University, co-first author), Hyun Uk Kim (KAIST, co-first author), and Sang Yup Lee (KAIST, corresponding author))
In this study, the research team developed DeepDDI2, an advanced version of DeepDDI, an AI-based drug interaction prediction model they developed in 2018. DeepDDI2 is able to compute for and process a total of 113 drug-drug interaction (DDI) types, more than the 86 DDI types covered by the existing DeepDDI.
The research team used DeepDDI2 to predict possible interactions between the ingredients (ritonavir, nirmatrelvir) of Paxlovid*, a COVID-19 treatment, and other prescription drugs. The research team said that while among COVID-19 patients, high-risk patients with chronic diseases such as high blood pressure and diabetes are likely to be taking other drugs, drug-drug interactions and adverse drug reactions for Paxlovid have not been sufficiently analyzed, yet. This study was pursued in light of seeing how continued usage of the drug may lead to serious and unwanted complications.
* Paxlovid: Paxlovid is a COVID-19 treatment developed by Pfizer, an American pharmaceutical company, and received emergency use approval (EUA) from the US Food and Drug Administration (FDA) in December 2021.
The research team used DeepDDI2 to predict how Paxrovid's components, ritonavir and nirmatrelvir, would interact with 2,248 prescription drugs. As a result of the prediction, ritonavir was predicted to interact with 1,403 prescription drugs and nirmatrelvir with 673 drugs.
Using the prediction results, the research team proposed alternative drugs with the same mechanism but low drug interaction potential for prescription drugs with high adverse drug events (ADEs). Accordingly, 124 alternative drugs that could reduce the possible adverse DDI with ritonavir and 239 alternative drugs for nirmatrelvir were identified.
Through this research achievement, it became possible to use an deep learning technology to accurately predict drug-drug interactions (DDIs), and this is expected to play an important role in the digital healthcare, precision medicine and pharmaceutical industries by providing useful information in the process of developing new drugs and making prescriptions.
Distinguished Professor Sang Yup Lee said, "The results of this study are meaningful at times like when we would have to resort to using drugs that are developed in a hurry in the face of an urgent situations like the COVID-19 pandemic, that it is now possible to identify and take necessary actions against adverse drug reactions caused by drug-drug interactions very quickly.”
This research was carried out with the support of the KAIST New-Deal Project for COVID-19 Science and Technology and the Bio·Medical Technology Development Project supported by the Ministry of Science and ICT.
Figure 1. Results of drug interaction prediction between Paxlovid ingredients and representative approved drugs using DeepDDI2
2023.03.16 View 5120 -
The cause of disability in aged brain meningeal membranes identified
Due to the increase in average age, studies on changes in the brain following general aging process without serious brain diseases have also become an issue that requires in-depth studies. Regarding aging research, as aging progresses, ‘sugar’ accumulates in the body, and the accumulated sugar becomes a causative agent for various diseases such as aging-related inflammation and vascular disease. In the end, “surplus” sugar molecules attach to various proteins in the body and interfere with their functions.
KAIST (President Kwang Hyung Lee), a joint research team of Professor Pilnam Kim and Professor Yong Jeong of the Department of Bio and Brain Engineering, revealed on the 15th that it was confirmed that the function of being the “front line of defense” for the cerebrocortex of the brain meninges, the layers of membranes that surrounds the brain, is hindered when 'sugar' begins to build up on them as aging progresses.
Professor Kim's research team confirmed excessive accumulation of sugar molecules in the meninges of the elderly and also confirmed that sugar accumulation occurs mouse models in accordance with certain age levels. The meninges are thin membranes that surround the brain and exist at the boundary between the cerebrospinal fluid and the cortex and play an important role in protecting the brain. In this study, it was revealed that the dysfunction of these brain membranes caused by aging is induced by 'excess' sugar in the brain. In particular, as the meningeal membrane becomes thinner and stickier due to aging, a new paradigm has been provided for the discovery of the principle of the decrease in material exchange between the cerebrospinal fluid and the cerebral cortex.
This research was conducted by the Ph.D. candidate Hyo Min Kim and Dr. Shinheun Kim as the co-first authors to be published online on February 28th in the international journal, Aging Cell. (Paper Title: Glycation-mediated tissue-level remodeling of brain meningeal membrane by aging)
The meninges, which are in direct contact with the cerebrospinal fluid, are mainly composed of collagen, an extracellular matrix (ECM) protein, and are composed of fibroblasts, which are cells that produce this protein. The cells that come in contact with collagen proteins that are attached with sugar have a low collagen production function, while the meningeal membrane continuously thins and collapses as the expression of collagen degrading enzymes increases.
Studies on the relationship between excess sugar molecules accumulation in the brain due to continued sugar intake and the degeneration of neurons and brain diseases have been continuously conducted. However, this study was the first to identify meningeal degeneration and dysfunction caused by glucose accumulation with the focus on the meninges itself, and the results are expected to present new ideas for research into approach towards discoveries of new treatments for brain disease.
Researcher Hyomin Kim, the first author, introduced the research results as “an interesting study that identified changes in the barriers of the brain due to aging through a convergent approach, starting from the human brain and utilizing an animal model with a biomimetic meningeal model”.
Professor Pilnam Kim's research team is conducting research and development to remove sugar that accumulated throughout the human body, including the meninges. Advanced glycation end products, which are waste products formed when proteins and sugars meet in the human body, are partially removed by macrophages. However, glycated products bound to extracellular matrix proteins such as collagen are difficult to remove naturally. Through the KAIST-Ceragem Research Center, this research team is developing a healthcare medical device to remove 'sugar residue' in the body.
This study was carried out with the National Research Foundation of Korea's collective research support.
Figure 1. Schematic diagram of proposed mechanism showing aging‐related ECM remodeling through meningeal fibroblasts on the brain leptomeninges. Meningeal fibroblasts in the young brain showed dynamic COL1A1 synthetic and COL1‐interactive function on the collagen membrane. They showed ITGB1‐mediated adhesion on the COL1‐composed leptomeningeal membrane and induction of COL1A1 synthesis for maintaining the collagen membrane. With aging, meningeal fibroblasts showed depletion of COL1A1 synthetic function and altered cell–matrix interaction.
Figure 2. Representative rat meningeal images observed in the study. Compared to young rats, it was confirmed that type 1 collagen (COL1) decreased along with the accumulation of glycated end products (AGE) in the brain membrane of aged rats, and the activity of integrin beta 1 (ITGB1), a representative receptor corresponding to cell-collagen interaction. Instead, it was observed that the activity of discoidin domain receptor 2 (DDR2), one of the tyrosine kinases, increased.
Figure 3. Substance flux through the brain membrane decreases with aging. It was confirmed that the degree of adsorption of fluorescent substances contained in cerebrospinal fluid (CSF) to the brain membrane increased and the degree of entry into the periphery of the cerebral blood vessels decreased in the aged rats. In this study, only the influx into the brain was confirmed during the entry and exit of substances, but the degree of outflow will also be confirmed through future studies.
2023.03.15 View 4555 -
KAIST develops 'MetaVRain' that realizes vivid 3D real-life images
KAIST (President Kwang Hyung Lee) is a high-speed, low-power artificial intelligence (AI: Artificial Intelligent) semiconductor* MetaVRain, which implements artificial intelligence-based 3D rendering that can render images close to real life on mobile devices.
* AI semiconductor: Semiconductor equipped with artificial intelligence processing functions such as recognition, reasoning, learning, and judgment, and implemented with optimized technology based on super intelligence, ultra-low power, and ultra-reliability
The artificial intelligence semiconductor developed by the research team makes the existing ray-tracing*-based 3D rendering driven by GPU into artificial intelligence-based 3D rendering on a newly manufactured AI semiconductor, making it a 3D video capture studio that requires enormous costs. is not needed, so the cost of 3D model production can be greatly reduced and the memory used can be reduced by more than 180 times. In particular, the existing 3D graphic editing and design, which used complex software such as Blender, is replaced with simple artificial intelligence learning, so the general public can easily apply and edit the desired style.
* Ray-tracing: Technology that obtains images close to real life by tracing the trajectory of all light rays that change according to the light source, shape and texture of the object
This research, in which doctoral student Donghyun Han participated as the first author, was presented at the International Solid-State Circuit Design Conference (ISSCC) held in San Francisco, USA from February 18th to 22nd by semiconductor researchers from all over the world.
(Paper Number 2.7, Paper Title: MetaVRain: A 133mW Real-time Hyper-realistic 3D NeRF Processor with 1D-2D Hybrid Neural Engines for Metaverse on Mobile Devices (Authors: Donghyeon Han, Junha Ryu, Sangyeob Kim, Sangjin Kim, and Hoi-Jun Yoo))
Professor Yoo's team discovered inefficient operations that occur when implementing 3D rendering through artificial intelligence, and developed a new concept semiconductor that combines human visual recognition methods to reduce them. When a person remembers an object, he has the cognitive ability to immediately guess what the current object looks like based on the process of starting with a rough outline and gradually specifying its shape, and if it is an object he saw right before. In imitation of such a human cognitive process, the newly developed semiconductor adopts an operation method that grasps the rough shape of an object in advance through low-resolution voxels and minimizes the amount of computation required for current rendering based on the result of rendering in the past.
MetaVRain, developed by Professor Yu's team, achieved the world's best performance by developing a state-of-the-art CMOS chip as well as a hardware architecture that mimics the human visual recognition process. MetaVRain is optimized for artificial intelligence-based 3D rendering technology and achieves a rendering speed of up to 100 FPS or more, which is 911 times faster than conventional GPUs. In addition, as a result of the study, the energy efficiency, which represents the energy consumed per video screen processing, is 26,400 times higher than that of GPU, opening the possibility of artificial intelligence-based real-time rendering in VR/AR headsets and mobile devices.
To show an example of using MetaVRain, the research team developed a smart 3D rendering application system together, and showed an example of changing the style of a 3D model according to the user's preferred style. Since you only need to give artificial intelligence an image of the desired style and perform re-learning, you can easily change the style of the 3D model without the help of complicated software. In addition to the example of the application system implemented by Professor Yu's team, it is expected that various application examples will be possible, such as creating a realistic 3D avatar modeled after a user's face, creating 3D models of various structures, and changing the weather according to the film production environment. do.
Starting with MetaVRain, the research team expects that the field of 3D graphics will also begin to be replaced by artificial intelligence, and revealed that the combination of artificial intelligence and 3D graphics is a great technological innovation for the realization of the metaverse.
Professor Hoi-Jun Yoo of the Department of Electrical and Electronic Engineering at KAIST, who led the research, said, “Currently, 3D graphics are focused on depicting what an object looks like, not how people see it.” The significance of this study was revealed as a study that enabled efficient 3D graphics by borrowing the way people recognize and express objects by imitating them.” He also foresaw the future, saying, “The realization of the metaverse will be achieved through innovation in artificial intelligence technology and innovation in artificial intelligence semiconductors, as shown in this study.”
Figure 1. Description of the MetaVRain demo screen
Photo of Presentation at the International Solid-State Circuits Conference (ISSCC)
2023.03.13 View 4513 -
KAIST team develops smart immune system that can pin down on malignant tumors
A joint research team led by Professor Jung Kyoon Choi of the KAIST Department of Bio and Brain Engineering and Professor Jong-Eun Park of the KAIST Graduate School of Medical Science and Engineering (GSMSE) announced the development of the key technologies to treat cancers using smart immune cells designed based on AI and big data analysis. This technology is expected to be a next-generation immunotherapy that allows precision targeting of tumor cells by having the chimeric antigen receptors (CARs) operate through a logical circuit. Professor Hee Jung An of CHA Bundang Medical Center and Professor Hae-Ock Lee of the Catholic University of Korea also participated in this research to contribute joint effort.
Professor Jung Kyoon Choi’s team built a gene expression database from millions of cells, and used this to successfully develop and verify a deep-learning algorithm that could detect the differences in gene expression patterns between tumor cells and normal cells through a logical circuit. CAR immune cells that were fitted with the logic circuits discovered through this methodology could distinguish between tumorous and normal cells as a computer would, and therefore showed potentials to strike only on tumor cells accurately without causing unwanted side effects.
This research, conducted by co-first authors Dr. Joonha Kwon of the KAIST Department of Bio and Brain Engineering and Ph.D. candidate Junho Kang of KAIST GSMSE, was published by Nature Biotechnology on February 16, under the title Single-cell mapping of combinatorial target antigens for CAR switches using logic gates.
An area in cancer research where the most attempts and advances have been made in recent years is immunotherapy. This field of treatment, which utilizes the patient’s own immune system in order to overcome cancer, has several methods including immune checkpoint inhibitors, cancer vaccines and cellular treatments. Immune cells like CAR-T or CAR-NK equipped with chimera antigen receptors, in particular, can recognize cancer antigens and directly destroy cancer cells.
Starting with its success in blood cancer treatment, scientists have been trying to expand the application of CAR cell therapy to treat solid cancer. But there have been difficulties to develop CAR cells with effective killing abilities against solid cancer cells with minimized side effects. Accordingly, in recent years, the development of smarter CAR engineering technologies, i.e., computational logic gates such as AND, OR, and NOT, to effectively target cancer cells has been underway.
At this point in time, the research team built a large-scale database for cancer and normal cells to discover the exact genes that are expressed only from cancer cells at a single-cell level. The team followed this up by developing an AI algorithm that could search for a combination of genes that best distinguishes cancer cells from normal cells. This algorithm, in particular, has been used to find a logic circuit that can specifically target cancer cells through cell-level simulations of all gene combinations. CAR-T cells equipped with logic circuits discovered through this methodology are expected to distinguish cancerous cells from normal cells like computers, thereby minimizing side effects and maximizing the effects of chemotherapy.
Dr. Joonha Kwon, who is the first author of this paper, said, “this research suggests a new method that hasn’t been tried before. What’s particularly noteworthy is the process in which we found the optimal CAR cell circuit through simulations of millions of individual tumors and normal cells.” He added, “This is an innovative technology that can apply AI and computer logic circuits to immune cell engineering. It would contribute greatly to expanding CAR therapy, which is being successfully used for blood cancer, to solid cancers as well.”
This research was funded by the Original Technology Development Project and Research Program for Next Generation Applied Omic of the Korea Research Foundation.
Figure 1. A schematic diagram of manufacturing and administration process of CAR therapy and of cancer cell-specific dual targeting using CAR.
Figure 2. Deep learning (convolutional neural networks, CNNs) algorithm for selection of dual targets based on gene combination (left) and algorithm for calculating expressing cell fractions by gene combination according to logical circuit (right).
2023.03.09 View 6028 -
KAIST presents a fundamental technology to remove metastatic traits from lung cancer cells
KAIST (President Kwang Hyung Lee) announced on January 30th that a research team led by Professor Kwang-Hyun Cho from the Department of Bio and Brain Engineering succeeded in using systems biology research to change the properties of carcinogenic cells in the lungs and eliminate both drug resistance and their ability to proliferate out to other areas of the body.
As the incidences of cancer increase within aging populations, cancer has become the most lethal disease threatening healthy life. Fatality rates are especially high when early detection does not happen in time and metastasis has occurred in various organs. In order to resolve this problem, a series of attempts were made to remove or lower the ability of cancer cells to spread, but they resulted in cancer cells in the intermediate state becoming more unstable and even more malignant, which created serious treatment challenges.
Professor Kwang-Hyun Cho's research team simulated various cancer cell states in the Epithelial-to-Mesenchymal Transition (EMT) of lung cancer cells, between epithelial cells without metastatic ability and mesenchymal cells with metastatic ability. A mathematical model of molecular network was established, and key regulators that could reverse the state of invasive and drug resistant mesenchymal cells back to the epithelial state were discovered through computer simulation analysis and molecular cell experiments. In particular, this process succeeded in properly reverting the mesenchymal lung cancer cells to a state where they were sensitive to chemotherapy treatment while avoiding the unstable EMT hybrid cell state in the middle process, which had remained a difficult problem.
The results of this research, in which KAIST Ph.D. student Namhee Kim, Dr. Chae Young Hwang, Researcher Taeyoung Kim, and Ph.D. student Hyunjin Kim participated, were published as an online paper in the international journal “Cancer Research” published by the American Association for Cancer Research (AACR) on January 30th. (Paper title: A cell fate reprogramming strategy reverses epithelial-to-mesenchymal transition of lung cancer cells while avoiding hybrid states)
Cells in an EMT hybrid state, which are caused by incomplete transitions during the EMT process in cancer cells, have the characteristics of both epithelial cells and mesenchymal cells, and are known to have high drug resistance and metastatic potential by acquiring high stem cell capacity. In particular, EMT is further enhanced through factors such as transforming growth factor-beta (TGF-β) secreted from the tumor microenvironment (TME) and, as a result, various cell states with high plasticity appear. Due to the complexity of EMT, it has been very difficult to completely reverse the transitional process of the mesenchymal cancer cells to an epithelial cell state in which metastatic ability and drug resistance are eliminated while avoiding the EMT hybrid cell state with high metastatic ability and drug resistance.
Professor Kwang-Hyun Cho's research team established a mathematical model of the gene regulation network that governs the complex process of EMT, and then applied large-scale computer simulation analysis and complex system network control technology to identify and verify 'p53', 'SMAD4', and 'ERK1' and 'ERK 2' (collectively ERKs) through molecular cell experiments as the three key molecular targets that can transform lung cancer cells in the mesenchymal cell state, reversed back to an epithelial cell state that no longer demonstrates the ability to metastasize, while avoiding the EMT hybrid cell state.
In particular, by analyzing the molecular regulatory mechanism of the complex EMT process at the system level, the key pathways were identified that were linked to the positive feedback that plays an important role in completely returning cancer cells to an epithelial cell state in which metastatic ability and drug resistance are removed.
This discovery is significant in that it proved that mesenchymal cells can be reverted to the state of epithelial cells under conditions where TGF-β stimulation are present, like they are in the actual environment where cancer tissue forms in the human body.
Abnormal EMT in cancer cells leads to various malignant traits such as the migration and invasion of cancer cells, changes in responsiveness to chemotherapy treatment, enhanced stem cell function, and the dissemination of cancer. In particular, the acquisition of the metastatic ability of cancer cells is a key determinant factor for the prognosis of cancer patients. The EMT reversal technology in lung cancer cells developed in this research is a new anti-cancer treatment strategy that reprograms cancer cells to eliminate their high plasticity and metastatic potential and increase their responsiveness to chemotherapy.
Professor Kwang-Hyun Cho said, "By succeeding in reversing the state of lung cancer cells that acquired high metastatic traits and resistance to drugs and reverting them to a treatable epithelial cell state with renewed sensitivity to chemotherapy, the research findings propose a new strategy for treatments that can improve the prognosis of cancer patients.”
Professor Kwang-Hyun Cho's research team was the first to present the principle of reversal treatment to revert cancer cells to normal cells, following through with the announcement of the results of their study that reverted colon cancer cells to normal colon cells in January of 2020, and also presenting successful re-programming research where the most malignant basal type breast cancer cells turned into less-malignant luminal type breast cancer cells that were treatable with hormonal therapies in January of 2022. This latest research result is the third in the development of reversal technology where lung cancer cells that had acquired metastatic traits returned to a state in which their metastatic ability was removed and drug sensitivity was enhanced.
This research was carried out with support from the Ministry of Science and ICT and the National Research Foundation of Korea's Basic Research in Science & Engineering Program for Mid-Career Researchers.
< Figure 1. Construction of the mathematical model of the regulatory network to represent the EMT phenotype based on the interaction between various molecules related to EMT.
(A) Professor Kwang-Hyun Cho's research team investigated numerous literatures and databases related to complex EMT, and based on comparative analysis of cell line data showing epithelial and mesenchymal cell conditions, they extracted key signaling pathways related to EMT and built a mathematical model of regulatory network (B) By comparing the results of computer simulation analysis and the molecular cell experiments, it was verified how well the constructed mathematical model simulated the actual cellular phenomena. >
< Figure 2. Understanding of various EMT phenotypes through large-scale computer simulation analysis and complex system network control technology.
(A) Through computer simulation analysis and experiments, Professor Kwang-Hyun Cho's research team found that complete control of EMT is impossible with single-molecule control alone. In particular, through comparison of the relative stability of attractors, it was revealed that the cell state exhibiting EMT hybrid characteristics has unstable properties. (B), (C) Based on these results, Prof. Cho’s team identified two feedbacks (positive feedback consisting of Snail-miR-34 and ZEB1-miR-200) that play an important role in avoiding the EMT hybrid state that appeared in the TGF-β-ON state. It was found through computer simulation analysis that the two feedbacks restore relatively high stability when the excavated p53 and SMAD4 are regulated. In addition, molecular cell experiments demonstrated that the expression levels of E-cad and ZEB1, which are representative phenotypic markers of EMT, changed similarly to the expression profile in the epithelial cell state, despite the TGF-β-ON state. >
< Figure 3. Complex molecular network analysis and discovery of reprogramming molecular targets for intact elimination of EMT hybrid features.
(A) Controlling the expression of p53 and SMAD4 in lung cancer cell lines was expected to overcome drug resistance, but contrary to expectations, chemotherapy responsiveness was not restored. (B) Professor Kwang-Hyun Cho's research team additionally analyzed computer simulations, genome data, and experimental results and found that high expression levels of TWIST1 and EPCAM were related to drug resistance. (C) Prof. Cho’s team identified three key molecular targets: p53, SMAD4 and ERK1 & ERK2. (D), (E) Furthermore, they identified a key pathway that plays an important role in completely reversing into epithelial cells while avoiding EMT hybrid characteristics, and confirmed through network analysis and attractor analysis that high stability of the key pathway was restored when the proposed molecular target was controlled. >
< Figure 4. Verification through experiments with lung cancer cell lines.
When p53 was activated and SMAD4 and ERK1/2 were inhibited in lung cancer cell lines, (A), (B) E-cad protein expression increased and ZEB1 protein expression decreased, and (C) mesenchymal cell status including TWIST1 and EPCAM and gene expression of markers related to stem cell potential characteristics were completely inhibited. In addition, (D) it was confirmed that resistance to chemotherapy treatment was also overcome as the cell state was reversed by the regulated target. >
< Figure 5. A schematic representation of the research results.
Prof. Cho’s research team identified key molecular regulatory pathways to avoid high plasticity formed by abnormal EMT of cancer cells and reverse it to an epithelial cell state through systems biology research. From this analysis, a reprogramming molecular target that can reverse the state of mesenchymal cells with acquired invasiveness and drug resistance to the state of epithelial cells with restored drug responsiveness was discovered.
For lung cancer cells, when a drug that enhances the expression of p53, one of the molecular targets discovered, and inhibits the expression of SMAD4 and ERK1 & ERK2 is administered, the molecular network of genes in the state of mesenchymal cells is modified, eventually eliminating metastatic ability and it is reprogrammed to turn into epithelial cells without the resistance to chemotherapy treatments. >
2023.01.30 View 11726 -
KAIST’s Robo-Dog “RaiBo” runs through the sandy beach
KAIST (President Kwang Hyung Lee) announced on the 25th that a research team led by Professor Jemin Hwangbo of the Department of Mechanical Engineering developed a quadrupedal robot control technology that can walk robustly with agility even in deformable terrain such as sandy beach.
< Photo. RAI Lab Team with Professor Hwangbo in the middle of the back row. >
Professor Hwangbo's research team developed a technology to model the force received by a walking robot on the ground made of granular materials such as sand and simulate it via a quadrupedal robot. Also, the team worked on an artificial neural network structure which is suitable in making real-time decisions needed in adapting to various types of ground without prior information while walking at the same time and applied it on to reinforcement learning. The trained neural network controller is expected to expand the scope of application of quadrupedal walking robots by proving its robustness in changing terrain, such as the ability to move in high-speed even on a sandy beach and walk and turn on soft grounds like an air mattress without losing balance.
This research, with Ph.D. Student Soo-Young Choi of KAIST Department of Mechanical Engineering as the first author, was published in January in the “Science Robotics”. (Paper title: Learning quadrupedal locomotion on deformable terrain).
Reinforcement learning is an AI learning method used to create a machine that collects data on the results of various actions in an arbitrary situation and utilizes that set of data to perform a task. Because the amount of data required for reinforcement learning is so vast, a method of collecting data through simulations that approximates physical phenomena in the real environment is widely used.
In particular, learning-based controllers in the field of walking robots have been applied to real environments after learning through data collected in simulations to successfully perform walking controls in various terrains.
However, since the performance of the learning-based controller rapidly decreases when the actual environment has any discrepancy from the learned simulation environment, it is important to implement an environment similar to the real one in the data collection stage. Therefore, in order to create a learning-based controller that can maintain balance in a deforming terrain, the simulator must provide a similar contact experience.
The research team defined a contact model that predicted the force generated upon contact from the motion dynamics of a walking body based on a ground reaction force model that considered the additional mass effect of granular media defined in previous studies.
Furthermore, by calculating the force generated from one or several contacts at each time step, the deforming terrain was efficiently simulated.
The research team also introduced an artificial neural network structure that implicitly predicts ground characteristics by using a recurrent neural network that analyzes time-series data from the robot's sensors.
The learned controller was mounted on the robot 'RaiBo', which was built hands-on by the research team to show high-speed walking of up to 3.03 m/s on a sandy beach where the robot's feet were completely submerged in the sand. Even when applied to harder grounds, such as grassy fields, and a running track, it was able to run stably by adapting to the characteristics of the ground without any additional programming or revision to the controlling algorithm.
In addition, it rotated with stability at 1.54 rad/s (approximately 90° per second) on an air mattress and demonstrated its quick adaptability even in the situation in which the terrain suddenly turned soft.
The research team demonstrated the importance of providing a suitable contact experience during the learning process by comparison with a controller that assumed the ground to be rigid, and proved that the proposed recurrent neural network modifies the controller's walking method according to the ground properties.
The simulation and learning methodology developed by the research team is expected to contribute to robots performing practical tasks as it expands the range of terrains that various walking robots can operate on.
The first author, Suyoung Choi, said, “It has been shown that providing a learning-based controller with a close contact experience with real deforming ground is essential for application to deforming terrain.” He went on to add that “The proposed controller can be used without prior information on the terrain, so it can be applied to various robot walking studies.”
This research was carried out with the support of the Samsung Research Funding & Incubation Center of Samsung Electronics.
< Figure 1. Adaptability of the proposed controller to various ground environments. The controller learned from a wide range of randomized granular media simulations showed adaptability to various natural and artificial terrains, and demonstrated high-speed walking ability and energy efficiency. >
< Figure 2. Contact model definition for simulation of granular substrates. The research team used a model that considered the additional mass effect for the vertical force and a Coulomb friction model for the horizontal direction while approximating the contact with the granular medium as occurring at a point. Furthermore, a model that simulates the ground resistance that can occur on the side of the foot was introduced and used for simulation. >
2023.01.26 View 11468