GE
-
KAIST and Google Jointly Develop AI Curricula
KAIST selected the two professors who will develop AI curriculum under the auspices of the KAIST-Google Partnership for AI Education and Research. The Graduate School of AI announced the two authors among the 20 applicants who will develop the curriculum next year. They will be provided 7,500 USD per subject.
Professor Changho Suh from the School of Electrical Engineering and Professor Yong-Jin Yoon from the Department of Mechanical Engineering will use Google technology such as TensorFlow, Google Cloud, and Android to create the curriculum.
Professor Suh’s “TensorFlow for Information Theory and Convex Optimization “will be used for curriculum in the graduate courses and Professor Yoon’s “AI Convergence Project Based Learning (PBL)” will be used for online courses. Professor Yoon’s course will explore and define problems by utilizing AI and experiencing the process of developing products that use AI through design thinking, which involves product design, production, and verification. Professor Suh’s course will discus“information theory and convergence,” which uses basic sciences and engineering as well as AI, machine learning, and deep learning.
2019.12.04 View 11282 -
AI to Determine When to Intervene with Your Driving
(Professor Uichin Lee (left) and PhD candidate Auk Kim)
Can your AI agent judge when to talk to you while you are driving? According to a KAIST research team, their in-vehicle conservation service technology will judge when it is appropriate to contact you to ensure your safety.
Professor Uichin Lee from the Department of Industrial and Systems Engineering at KAIST and his research team have developed AI technology that automatically detects safe moments for AI agents to provide conversation services to drivers.
Their research focuses on solving the potential problems of distraction created by in-vehicle conversation services. If an AI agent talks to a driver at an inopportune moment, such as while making a turn, a car accident will be more likely to occur.
In-vehicle conversation services need to be convenient as well as safe. However, the cognitive burden of multitasking negatively influences the quality of the service. Users tend to be more distracted during certain traffic conditions. To address this long-standing challenge of the in-vehicle conversation services, the team introduced a composite cognitive model that considers both safe driving and auditory-verbal service performance and used a machine-learning model for all collected data.
The combination of these individual measures is able to determine the appropriate moments for conversation and most appropriate types of conversational services. For instance, in the case of delivering simple-context information, such as a weather forecast, driver safety alone would be the most appropriate consideration. Meanwhile, when delivering information that requires a driver response, such as a “Yes” or “No,” the combination of driver safety and auditory-verbal performance should be considered.
The research team developed a prototype of an in-vehicle conversation service based on a navigation app that can be used in real driving environments. The app was also connected to the vehicle to collect in-vehicle OBD-II/CAN data, such as the steering wheel angle and brake pedal position, and mobility and environmental data such as the distance between successive cars and traffic flow.
Using pseudo-conversation services, the research team collected a real-world driving dataset consisting of 1,388 interactions and sensor data from 29 drivers who interacted with AI conversational agents. Machine learning analysis based on the dataset demonstrated that the opportune moments for driver interruption could be correctly inferred with 87% accuracy.
The safety enhancement technology developed by the team is expected to minimize driver distractions caused by in-vehicle conversation services. This technology can be directly applied to current in-vehicle systems that provide conversation services. It can also be extended and applied to the real-time detection of driver distraction problems caused by the use of a smartphone while driving.
Professor Lee said, “In the near future, cars will proactively deliver various in-vehicle conversation services. This technology will certainly help vehicles interact with their drivers safely as it can fairly accurately determine when to provide conversation services using only basic sensor data generated by cars.”
The researchers presented their findings at the ACM International Joint Conference on Pervasive and Ubiquitous Computing (Ubicomp’19) in London, UK. This research was supported in part by Hyundai NGV and by the Next-Generation Information Computing Development Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science and ICT.
(Figure: Visual description of safe enhancement technology for in-vehicle conversation services)
2019.11.13 View 14822 -
Tungsten Suboxide Improves the Efficiency of Platinum in Hydrogen Production
< PhD Candidate Jinkyu Park and Professor Jinwoo Lee >
Researchers presented a new strategy for enhancing catalytic activity using tungsten suboxide as a single-atom catalyst (SAC). This strategy, which significantly improves hydrogen evolution reaction (HER) in metal platinum (pt) by 16.3 times, sheds light on the development of new electrochemical catalyst technologies.
Hydrogen has been touted as a promising alternative to fossil fuels. However, most of the conventional industrial hydrogen production methods come with environmental issues, releasing significant amounts of carbon dioxide and greenhouse gases.
Electrochemical water splitting is considered a potential approach for clean hydrogen production. Pt is one of the most commonly used catalysts to improve HER performance in electrochemical water splitting, but the high cost and scarcity of Pt remain key obstacles to mass commercial applications.
SACs, where all metal species are individually dispersed on a desired support material, have been identified as one way to reduce the amount of Pt usage, as they offer the maximum number of surface exposed Pt atoms.
Inspired by earlier studies, which mainly focused on SACs supported by carbon-based materials, a KAIST research team led by Professor Jinwoo Lee from the Department of Chemical and Biomolecular Engineering investigated the influence of support materials on the performance of SACs.
Professor Lee and his researchers suggested mesoporous tungsten suboxide as a new support material for atomically dispersed Pt, as this was expected to provide high electronic conductivity and have a synergetic effect with Pt.
They compared the performance of single-atom Pt supported by carbon and tungsten suboxide respectively. The results revealed that the support effect occurred with tungsten suboxide, in which the mass activity of a single-atom Pt supported by tungsten suboxide was 2.1 times greater than that of single-atom Pt supported by carbon, and 16.3 times higher than that of Pt nanoparticles supported by carbon.
The team indicated a change in the electronic structure of Pt via charge transfer from tungsten suboxide to Pt. This phenomenon was reported as a result of strong metal-support interaction between Pt and tungsten suboxide.
HER performance can be improved not only by changing the electronic structure of the supported metal, but also by inducing another support effect, the spillover effect, the research group reported. Hydrogen spillover is a phenomenon where adsorbed hydrogen migrates from one surface to another, and it occurs more easily as the Pt size becomes smaller.
The researchers compared the performance of single-atom Pt and Pt nanoparticles supported by tungsten suboxide. The single-atom Pt supported by tungsten suboxide exhibited a higher degree of hydrogen spillover phenomenon, which enhanced the Pt mass activity for hydrogen evolution up to 10.7 times compared to Pt nanoparticles supported by tungsten suboxide.
Professor Lee said, “Choosing the right support material is important for improving electrocatalysis in hydrogen production. The tungsten suboxide catalyst we used to support Pt in our study implies that interactions between the well-matched metal and support can drastically enhance the efficiency of the process.”
This research was supported by the Ministry of Science and ICT and introduced in the International Edition of the German journal Angewandte Chemie.
Figure. Schematic representation of hydrogen evolution reaction (HER) of pseudo single-atom Pt supported by tungsten suboxide
-Publication
Jinkyu Park, Dr. Seonggyu Lee, Hee-Eun Kim, Ara Cho, Seongbeen Kim, Dr. Youngjin Ye, Prof. Jeong Woo Han, Prof. Hyunjoo Lee, Dr. Jong Hyun Jang, and Prof. Jinwoo Lee. 2019. Investigation of the Support Effect in Atomically Dispersed Pt on WO3−x for Utilization of Pt in the Hydrogen Evolution Reaction. International Edition of Angewandte Chemie. Volume No. 58. Issue No. 45. 6 pages. https://doi.org/10.1002/anie.201908122
-ProfileProfessor Jinwoo LeeConvergence of Energy and Nano Science Laboratoryhttp://cens.kaist.ac.kr
Department of Chemical and Biomolecular EngineeringKAIST
2019.10.28 View 18831 -
Image Analysis to Automatically Quantify Gender Bias in Movies
Many commercial films worldwide continue to express womanhood in a stereotypical manner, a recent study using image analysis showed. A KAIST research team developed a novel image analysis method for automatically quantifying the degree of gender bias in films.
The ‘Bechdel Test’ has been the most representative and general method of evaluating gender bias in films. This test indicates the degree of gender bias in a film by measuring how active the presence of women is in a film. A film passes the Bechdel Test if the film (1) has at least two female characters, (2) who talk to each other, and (3) their conversation is not related to the male characters.
However, the Bechdel Test has fundamental limitations regarding the accuracy and practicality of the evaluation. Firstly, the Bechdel Test requires considerable human resources, as it is performed subjectively by a person. More importantly, the Bechdel Test analyzes only a single aspect of the film, the dialogues between characters in the script, and provides only a dichotomous result of passing the test, neglecting the fact that a film is a visual art form reflecting multi-layered and complicated gender bias phenomena. It is also difficult to fully represent today’s various discourse on gender bias, which is much more diverse than in 1985 when the Bechdel Test was first presented.
Inspired by these limitations, a KAIST research team led by Professor Byungjoo Lee from the Graduate School of Culture Technology proposed an advanced system that uses computer vision technology to automatically analyzes the visual information of each frame of the film. This allows the system to more accurately and practically evaluate the degree to which female and male characters are discriminatingly depicted in a film in quantitative terms, and further enables the revealing of gender bias that conventional analysis methods could not yet detect.
Professor Lee and his researchers Ji Yoon Jang and Sangyoon Lee analyzed 40 films from Hollywood and South Korea released between 2017 and 2018. They downsampled the films from 24 to 3 frames per second, and used Microsoft’s Face API facial recognition technology and object detection technology YOLO9000 to verify the details of the characters and their surrounding objects in the scenes.
Using the new system, the team computed eight quantitative indices that describe the representation of a particular gender in the films. They are: emotional diversity, spatial staticity, spatial occupancy, temporal occupancy, mean age, intellectual image, emphasis on appearance, and type and frequency of surrounding objects.
Figure 1. System Diagram
Figure 2. 40 Hollywood and Korean Films Analyzed in the Study
According to the emotional diversity index, the depicted women were found to be more prone to expressing passive emotions, such as sadness, fear, and surprise. In contrast, male characters in the same films were more likely to demonstrate active emotions, such as anger and hatred.
Figure 3. Difference in Emotional Diversity between Female and Male Characters
The type and frequency of surrounding objects index revealed that female characters and automobiles were tracked together only 55.7 % as much as that of male characters, while they were more likely to appear with furniture and in a household, with 123.9% probability.
In cases of temporal occupancy and mean age, female characters appeared less frequently in films than males at the rate of 56%, and were on average younger in 79.1% of the cases. These two indices were especially conspicuous in Korean films.
Professor Lee said, “Our research confirmed that many commercial films depict women from a stereotypical perspective. I hope this result promotes public awareness of the importance of taking prudence when filmmakers create characters in films.”
This study was supported by KAIST College of Liberal Arts and Convergence Science as part of the Venture Research Program for Master’s and PhD Students, and will be presented at the 22nd ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW) on November 11 to be held in Austin, Texas.
Publication:
Ji Yoon Jang, Sangyoon Lee, and Byungjoo Lee. 2019. Quantification of Gender Representation Bias in Commercial Films based on Image Analysis. In Proceedings of the 22nd ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW). ACM, New York, NY, USA, Article 198, 29 pages. https://doi.org/10.1145/3359300
Link to download the full-text paper:
https://files.cargocollective.com/611692/cscw198-jangA--1-.pdf
Profile: Prof. Byungjoo Lee, MD, PhD
byungjoo.lee@kaist.ac.kr
http://kiml.org/
Assistant Professor
Graduate School of Culture Technology (CT)
Korea Advanced Institute of Science and Technology (KAIST)
https://www.kaist.ac.kr Daejeon 34141, Korea
Profile: Ji Yoon Jang, M.S.
yoone3422@kaist.ac.kr
Interactive Media Lab
Graduate School of Culture Technology (CT)
Korea Advanced Institute of Science and Technology (KAIST)
https://www.kaist.ac.kr Daejeon 34141, Korea
Profile: Sangyoon Lee, M.S. Candidate
sl2820@kaist.ac.kr
Interactive Media Lab
Graduate School of Culture Technology (CT)
Korea Advanced Institute of Science and Technology (KAIST)
https://www.kaist.ac.kr Daejeon 34141, Korea
(END)
2019.10.17 View 22696 -
Two Professors Recognized for the National R&D Excellence 100
< Professor Haeng-Ki Lee (left) and Professor Jeong-Ho Lee (right) >
Two KAIST professors were listed among the 2019 National R&D Excellence 100 announced by the Ministry of Science and ICT and the Korea Institute of S&T Evaluation and Planning.
Professor Haeng-Ki Lee from the Department of Civil and Environmental Engineering was recognized in the field of mechanics and materials for his research on developing new construction materials through the convergence of nano- and biotechnologies.
In the field of life and marine science, Professor Jeong-Ho Lee from the Graduate School of Medical Science and Engineering was lauded for his research of diagnostic tools and therapies for glioblastoma and pediatric brain tumors.
A certificate from the Minister of Ministry of Science and ICT will be conferred to these two professors, and their names will be inscribed on a special 2019 National R&D Excellence 100 plaque to celebrate their achievements. The professors will also be given privileges during the process of new R&D project selection.
(END)
2019.10.15 View 9479 -
Sungjoon Park Named Google PhD Fellow
PhD candidate Sungjoon Park from the School of Computing was named a 2019 Google PhD Fellow in the field of natural language processing. The Google PhD fellowship program has recognized and supported outstanding graduate students in computer science and related fields since 2009. Park is one of three Korean students chosen as the recipients of Google Fellowships this year. A total of 54 students across the world in 12 fields were awarded this fellowship.
Park’s research on computational psychotherapy using natural language processing (NLP) powered by machine learning earned him this year’s fellowship. He presented of learning distributed representations in Korean and their interpretations during the 2017 Annual Conference of the Association for Computational Linguistics and the 2018 Conference on Empirical Methods in Natural Language Processing. He also applied machine learning-based natural language processing into computational psychotherapy so that a trained machine learning model could categorize client's verbal responses in a counseling dialogue. This was presented at the Annual Conference of the North American Chapter of the Association for Computational Linguistics.
More recently, he has been developing on neural response generation model and the prediction and extraction of complex emotion in text, and computational psychotherapy applications.
2019.09.17 View 7018 -
Researchers Describe a Mechanism Inducing Self-Killing of Cancer Cells
(Professor Kim (left) and lead author Lee)
Researchers have described a new mechanism which induces the self-killing of cancer cells by perturbing ion homeostasis. A research team from the Department of Biochemical Engineering has developed helical polypeptide potassium ionophores that lead to the onset of programmed cell death. The ionophores increase the active oxygen concentration to stress endoplasmic reticulum to the point of cellular death.
The electrochemical gradient between extracellular and intracellular conditions plays an important role in cell growth and metabolism. When a cell’s ion homeostasis is disturbed, critical functions accelerating the activation of apoptosis are inhibited in the cell.
Although ionophores have been intensively used as an ion homeostasis disturber, the mechanisms of cell death have been unclear and the bio-applicability has been limited. In the study featured at Advanced Science, the team presented an alpha helical peptide-based anticancer agent that is capable of transporting potassium ions with water solubility. The cationic, hydrophilic, and potassium ionic groups were combined at the end of the peptide side chain to provide both ion transport and hydrophilic properties.
These peptide-based ionophores reduce the intracellular potassium concentration and at the same time increase the intracellular calcium concentration. Increased intracellular calcium concentrations produce intracellular reactive oxygen species, causing endoplasmic reticulum stress, and ultimately leading to apoptosis.
Anticancer effects were evaluated using tumor-bearing mice to confirm the therapeutic effect, even in animal models. It was found that tumor growth was strongly inhibited by endoplasmic stress-mediated apoptosis.
Lead author Dr. Dae-Yong Lee said, “A peptide-based ionophore is more effective than conventional chemotherapeutic agents because it induces apoptosis via elevated reactive oxygen species levels. Professor Yeu-Chun Kim said he expects this new mechanism to be widely used as a new chemotherapeutic strategy. This research was funded by the National Research Foundation.
2019.08.28 View 18134 -
Distinguished Professor Sukbok Chang Donates His Prize Money
The honoree of the 2019 Korea Best Scientist and Technologist Award, Distinguished Professor Sukbok Chang donated his prize money of one hundred million KRW to the Chemistry Department Scholarship Fund and the Lyu Keun-Chul Sports Complex Management Fund during a donation ceremony last week.
Professor Chang won the award last month in recognition of his pioneering achievements and lifetime contributions to the development of carbon-hydrogen activation strategies, especially for carbon-carbon, carbon-nitrogen, and carbon-oxygen formations. Professor Chang, a world renowned chemist, has been recognized for his highly selective catalytic systems, allowing the controlled defunctionalization of bio-derived platform substrates under mild conditions and opening a new avenue for the utilization of biomass-derived platform chemicals.
“All my achievements are the results of my students’ hard work and dedication. I feel very fortunate to have such talented team members. I want to express my sincere gratitude for such a great research environment that we have worked together in so far,” said Professor Chang at the ceremony.
KAIST President Sung-Chul Shin said, “Not only will Professor Chang’s donation make a significant contribution to the Department of Chemistry, but also to the improvement of the Lyu Keun-Chul Sports Complex’s management, which directly links to the health and welfare of the KAIST community.”
Professor Chang currently holds the position of distinguished professor at KAIST and director of the Center for Catalytic Hydrocarbon Functionalizations in the Institute for Basic Science (IBS). He previously received the Kyung-Ahm Academic Award in 2013 and the Korea Toray Science Award in 2018. All these prize money also went to the school.
(END)
2019.08.26 View 6848 -
Accurate Detection of Low-Level Somatic Mutation in Intractable Epilepsy
KAIST medical scientists have developed an advanced method for perfectly detecting low-level somatic mutation in patients with intractable epilepsy. Their study showed that deep sequencing replicates of major focal epilepsy genes accurately and efficiently identified low-level somatic mutations in intractable epilepsy.
According to the study, their diagnostic method could increase the accuracy up to 100%, unlike the conventional sequencing analysis, which stands at about 30% accuracy. This work was published in Acta Neuropathologica.
Epilepsy is a neurological disorder common in children. Approximately one third of child patients are diagnosed with intractable epilepsy despite adequate anti-epileptic medication treatment.
Somatic mutations in mTOR pathway genes, SLC35A2, and BRAF are the major genetic causes of intractable epilepsies. A clinical trial to target Focal Cortical Dysplasia type II (FCDII), the mTOR inhibitor is underway at Severance Hospital, their collaborator in Seoul, Korea. However, it is difficult to detect such somatic mutations causing intractable epilepsy because their mutational burden is less than 5%, which is similar to the level of sequencing artifacts. In the clinical field, this has remained a standing challenge for the genetic diagnosis of somatic mutations in intractable epilepsy.
Professor Jeong Ho Lee’s team at the Graduate School of Medical Science and Engineering analyzed paired brain and peripheral tissues from 232 intractable epilepsy patients with various brain pathologies at Severance Hospital using deep sequencing and extracted the major focal epilepsy genes.
They narrowed down target genes to eight major focal epilepsy genes, eliminating almost all of the false positive calls using deep targeted sequencing. As a result, the advanced method robustly increased the accuracy and enabled them to detect low-level somatic mutations in unmatched Formalin Fixed Paraffin Embedded (FFPE) brain samples, the most clinically relevant samples.
Professor Lee conducted this study in collaboration with Professor Dong Suk Kim and Hoon-Chul Kang at Severance Hospital of Yonsei University. He said, “This advanced method of genetic analysis will improve overall patient care by providing more comprehensive genetic counseling and informing decisions on alternative treatments.”
Professor Lee has investigated low-level somatic mutations arising in the brain for a decade. He is developing innovative diagnostics and therapeutics for untreatable brain disorders including intractable epilepsy and glioblastoma at a tech-startup called SoVarGen. “All of the technologies we used during the research were transferred to the company. This research gave us very good momentum to reach the next phase of our startup,” he remarked.
The work was supported by grants from the Suh Kyungbae Foundation, a National Research Foundation of Korea grant funded by the Ministry of Science and ICT, the Korean Health Technology R&D Project from the Ministry of Health & Welfare, and the Netherlands Organization for Health Research and Development.
(Figure: Landscape of somatic and germline mutations identified in intractable epilepsy patients. a Signaling pathways for all of the mutated genes identified in this study. Bold: somatic mutation, Regular: germline mutation. b The distribution of variant allelic frequencies (VAFs) of identified somatic mutations. c The detecting rate and types of identified mutations according to histopathology. Yellow: somatic mutations, green: two-hit mutations, grey: germline mutations.)
2019.08.14 View 27007 -
Synthesizing Single-Crystalline Hexagonal Graphene Quantum Dots
(Figure: Uniformly ordered single-crystalline graphene quantum dots of various sizes synthesized through solution chemistry.)
A KAIST team has designed a novel strategy for synthesizing single-crystalline graphene quantum dots, which emit stable blue light. The research team confirmed that a display made of their synthesized graphene quantum dots successfully emitted blue light with stable electric pressure, reportedly resolving the long-standing challenges of blue light emission in manufactured displays. The study, led by Professor O Ok Park in the Department of Chemical and Biological Engineering, was featured online in Nano Letters on July 5.
Graphene has gained increased attention as a next-generation material for its heat and electrical conductivity as well as its transparency. However, single and multi-layered graphene have characteristics of a conductor so that it is difficult to apply into semiconductor. Only when downsized to the nanoscale, semiconductor’s distinct feature of bandgap will be exhibited to emit the light in the graphene. This illuminating featuring of dot is referred to as a graphene quantum dot.
Conventionally, single-crystalline graphene has been fabricated by chemical vapor deposition (CVD) on copper or nickel thin films, or by peeling graphite physically and chemically. However, graphene made via chemical vapor deposition is mainly used for large-surface transparent electrodes. Meanwhile, graphene made by chemical and physical peeling carries uneven size defects.
The research team explained that their graphene quantum dots exhibited a very stable single-phase reaction when they mixed amine and acetic acid with an aqueous solution of glucose. Then, they synthesized single-crystalline graphene quantum dots from the self-assembly of the reaction intermediate. In the course of fabrication, the team developed a new separation method at a low-temperature precipitation, which led to successfully creating a homogeneous nucleation of graphene quantum dots via a single-phase reaction.
Professor Park and his colleagues have developed solution phase synthesis technology that allows for the creation of the desired crystal size for single nanocrystals down to 100 nano meters. It is reportedly the first synthesis of the homogeneous nucleation of graphene through a single-phase reaction.
Professor Park said, "This solution method will significantly contribute to the grafting of graphene in various fields. The application of this new graphene will expand the scope of its applications such as for flexible displays and varistors.”
This research was a joint project with a team from Korea University under Professor Sang Hyuk Im from the Department of Chemical and Biological Engineering, and was supported by the National Research Foundation of Korea, the Nano-Material Technology Development Program from the Electronics and Telecommunications Research Institute (ETRI), KAIST EEWS, and the BK21+ project from the Korean government.
2019.08.02 View 31129 -
'Flying Drones for Rescue'
(Video Credit: ⓒNASA JPL)
< Team USRG and Professor Shim (second from the right) >
Having recently won the AI R&D Grand Challenge Competition in Korea, Team USRG (Unmanned System Research Group) led by Professor Hyunchul Shim from the School of Electrical Engineering is all geared up to take on their next challenges: the ‘Defense Advanced Research Projects Agency Subterranean Challenge (DARPA SubT Challenge)’ and ‘Lockheed Martin’s AlphaPilot Challenge’ next month.
Team USRG won the obstacle course race in the ‘2019 AI R&D Grand Challenge Competition’ on July 12. They managed to successfully dominate the challenging category of ‘control intelligence.’ Having to complete the obstacle course race solely using AI systems without any connection to the internet made it difficult for most of the eight participating teams to pass the third section of the race, and only Team USRG passed the long pipeline course during their attempt in the main event. They also demonstrated, after the main event, that their drone can navigate all of the checkpoints including landing on the “H” mark using deep learning.
Their drone flew through polls and pipes, and escaped from windows and mazes against strong winds, amid cheers and groans from the crowd gathered at the Korea Exhibition Center (KINTEX) in Goyang, Korea. The team was awarded three million KRW in prize money, and received a research grant worth six hundred million KRW from the Ministry of Science and ICT (MSIT).
“Being ranked first in the race for which we were never given a chance for a test flight means a lot to our team. Considering that we had no information on the exact size of the course in advance, this is a startling result,” said Professor Shim. “We will carry out further research with this funding, and compete once again with the improved AI and drone technology in the 2020 competition,” he added.
The AI R&D Grand Challenge Competition, which was first started in 2017, has been designed to promote AI research and development and expand its application to addressing high-risk technical challenges with significant socio-economic impact.
This year’s competition presented participants with a task where they had to develop AI software technology for drones to navigate themselves autonomously during complex disaster relief operations such as aid delivery.
Each team participated in one of the four tracks of the competition, and their drones were evaluated based on the criteria for each track. The divisions were broken up into intelligent context-awareness, intelligent character recognition, auditory intelligence, and control intelligence.
Team USRG’s technological prowess has been already well acclaimed among international peer groups. Teamed up with NASA JPL, Caltech, and MIT, they will compete in the subterranean mission during the ‘DARPA SubT Challenge’.
Team CoSTAR, as its name stands for, is working together to build ‘Collaborative SubTerranean Autonomous Resilient Robots.’ Professor Shim emphasized the role KAIST plays in Team CoSTAR as a leader in drone technology.
“I think when our drone technology will be added to our peers’ AI and robotics, Team CoSTAR will bring out unsurpassable synergy in completing the subterrestrial and planetary applications. I would like to follow the footprint of Hubo, the winning champion of the 2015 DARPA Robotics Challenge and even extend it to subterranean exploration,” he said.
These next generation autonomous subsurface explorers are now all optimizing the physical AI robot systems developed by Team CoSTAR. They will test their systems in more realistic field environments August 15 through 22 in Pittsburgh, USA. They have already received funding from DARPA for participating.
Team CoSTAR will compete in three consecutive yearly events starting this year, and the last event, planned for 2021, will put the team to the final test with courses that incorporate diverse challenges from all three events. Two million USD will be awarded to the winner after the final event, with additional prizes of up to 200,000 USD for self-funded teams.
Team USRG also ranked third in the recent Hyundai Motor Company’s ‘Autonomous Vehicle Competition’ and another challenge is on the horizon: Lockheed Martin’s ‘AlphaPilot Challenge’. In this event, the teams will be flying their drones through a series of racing gates, trying to beat the best human pilot. The challenge is hosted by Lockheed Martin, the world’s largest military contractor and the maker of the famed F-22 and F-35 stealth fighters, with the goal of stimulating the development of autonomous drones. Team USRG was selected from out of more than 400 teams from around the world and is preparing for a series of races this fall, beginning from the end of August.
Professor Shim said, “It is not easy to perform in a series of competitions in just a few months, but my students are smart, hardworking, and highly motivated. These events indeed demand a lot, but they really challenge the researchers to come up with technologies that work in the real world. This is the way robotics really should be.”
(END)
2019.07.26 View 10123 -
Newly Identified Meningeal Lymphatic Vessels Answers the Key Questions on Brain Clearance
(Figure: Schematic images of location and features of meningeal lymphatic vessels and their changes associated with ageing.)
Just see what happens when your neighborhood’s waste disposal system is out of service. Not only do the piles of trash stink but they can indeed hinder the area’s normal functioning. That is also the case when the brain’s waste management is on the blink.
The buildup of toxic proteins in the brain causes a massive damage to the nerves, leading to cognitive dysfunction and increased probability of developing neurodegenerative disorders such as Alzheimer's disease. Though the brain drains its waste via the cerebrospinal fluid (CSF), little has been understood about an accurate route for the brain’s cleansing mechanism.
Medical scientists led by Professor Gou Young Koh at the Graduate School of Medical Science and Engineering have reported the basal side of the skull as the major route, so called “hotspot” for CSF drainage.
They found that basal meningeal lymphatic vessels (mLVs) function as the main plumbing pipes for CSF. They confirmed macromolecules in the CSF mainly runs through the basal mLVs. Notably, the team also revealed that the brain’s major drainage system, specifically basal mLVs are impaired with aging. Their findings have been reported in the journal Nature on July 24.
Throughout our body, excess fluids and waste products are removed from tissues via lymphatic vessels. It was only recently discovered that the brain also has a lymphatic drainage system. mLVs are supposed to carry waste from the brain tissue fluid and the CSF down the deep cervical lymph nodes for disposal. Still scientist are left with one perplexing question — where is the main exit for the CSF? Though mLVs in the upper part of the skull (dorsal meningeal lymphatic vessels) were reported as the brain’s clearance pathways in 2014, no substantial drainage mechanism was observed in that section.
“As a hidden exit for CSF, we looked into the mLVs trapped within complex structures at the base of the skull,” says Dr. Ji Hoon Ahn, the first author of this study. The researchers used several techniques to characterize the basal mLVs in detail. They used a genetically engineered lymphatic-reporter mouse model to visualize mLVs under a fluorescence microscope. By performing a careful examination of the mice skull, they found distinctive features of basal mLVs that make them suitable for CSF uptake and drainage. Just like typical functional lymphatic vessels, basal mLVs are found to have abundant lymphatic vessel branches with finger-like protrusions. Additionally, valves inside the basal mLVs allow the flow to go in one direction. In particular, they found that the basal mLVs are closely located to the CSF. Dr. Hyunsoo Cho, the first author of this study explains, “All up, it seemed a solid case that basal mLVs are the brain’s main clearance pathways.
The researchers verified such specialized morphologic characteristics of basal mLVs indeed facilitate the CSF uptake and drainage. Using CSF contrast-enhanced magnetic resonance imaging in a rat model, they found that CSF is drained preferentially through the basal mLVs. They also utilized a lymphatic-reporter mouse model and discovered that fluorescence-tagged tracer injected into the brain itself or the CSF is cleared mainly through the basal mLVs. Jun-Hee Kim, the first author of this study notes, “We literally saw that the brain clearance mechanism utilizing basal outflow route to exit the skull.
It has long been suggested that CSF turnover and drainage declines with ageing. However, alteration of mLVs associated with ageing is poorly understood. In this study, the researchers observed changes of mLVs in young (3-month-old) and aged (24~27-months-old) mice. They found that the structure of the basal mLVs and their lymphatic valves in aged mice become severely flawed, thus hampering CSF clearance. The corresponding author of this study, Dr. Koh says, “By characterizing the precise route for fluids leaving the brain, this study improves our understanding on how waste is cleared from the brain. Our findings also provide further insights into the role of impaired CSF clearance in the development of age-related neurodegenerative diseases.”
Many current therapies for Alzheimer’s disease target abnormally accumulated proteins, such as beta-amyloid. By mapping out a precise route for the brain’s waste clearance system, this study may be able to help find ways to improve the brain’s cleansing function. Such breakthrough might become quite a sensational strategy for eliminating the buildup of aging-related toxic proteins. “It definitely warrants more extensive investigation of mLVs in patients with age-related neurodegenerative disease such as Alzheimer’s disease prior to clinical investigation,” adds Professor Koh.
2019.07.25 View 31117