Kaist

Object Identification ＆ Interaction with a Smartph..

                     (Professor Lee (far right) demonstrate 'Knocker' with his students.)                          A KAIST team has featured a new technology, “Knocker”, which identifies objects and executes actions just by knocking on it with the smartphone. Software powered by machine learning of sounds, vibrations, and other reactions will perform the users’ directions.  What separates Knocker from existing technology is the sensor fusion of sound and motion. Previously, object identification used either computer vision technology with cameras or hardware such as RFID (Radio Frequency Identification) tags. These solutions all have their limitations. For computer vision technology, users need to take pictures of every item. Even worse, the technology will not work well in poor lighting situations. Using hardware leads to additional costs and labor burdens. Knocker, on the other hand, can identify objects even in dark environments only with a smartphone, without requiring any specialized hardware or using a camera. Knocker utilizes the smartphone’s built-in sensors such as a microphone, an accelerometer, and a gyroscope to capture a unique set of responses generated when a smartphone is knocked against an object. Machine learning is used to analyze these responses and classify and identify objects. The research team under Professor Sung-Ju Lee from the School of Computing confirmed the applicability of Knocker technology using 23 everyday objects such as books, laptop computers, water bottles, and bicycles. In noisy environments such as a busy café or on the side of a road, it achieved 83％ identification accuracy. In a quiet indoor environment, the accuracy rose to 98％. The team believes Knocker will open a new paradigm of object interaction. For instance, by knocking on an empty water bottle, a smartphone can automatically order new water bottles from a merchant app. When integrated with IoT devices, knocking on a bed’s headboard before going to sleep could turn off the lights and set an alarm. The team suggested and implemented 15 application cases in the paper, presented during the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2019) held in London last month. Professor Sung-Ju Lee said, “This new technology does not require any specialized sensor or hardware. It simply uses the built-in sensors on smartphones and takes advantage of the power of machine learning. It’s a software solution that everyday smartphone users could immediately benefit from.” He continued, “This technology enables users to conveniently interact with their favorite objects.” The research was supported in part by the Next-Generation Information Computing Development Program through the National Research Foundation of Korea funded by the Ministry of Science and ICT and an Institute for Information & Communications Technology Promotion (IITP) grant funded by the Ministry of Science and ICT.       Figure: An example knock on a bottle. Knocker identifies the object by analyzing a unique set of responses from the knock, and automatically launches a proper application or service.

Professor Hyun Gyu Park Appointed as Associate Edi..

   Professor Hyun Gyu Park from the Department of Chemical and Biomolecular Engineering was appointed as an associate editor for Biosensors and Bioelectronics, an international journal published by Elsevier.   Biosensors and Bioelectronics is one of the top SCI journals in the fields of chemistry and analytical science (IF 9.518 as of 2018). Professor Park was recognized and appointed as the associate editor for this journal due to his outstanding research achievements in the fields of nucleic acid engineering, biosensors, and nanobiotechnology.   Professor Park will serve as the associate editor from this October until December 2021.

Sungjoon Park Named Google PhD Fellow

(PhD candidate Sungjoon Park) 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.

Algorithm Identifies Optimal Pairs for Composing M..

The integration of metal-organic frameworks (MOFs) and other metal nanoparticles has increasingly led to the creation of new multifunctional materials. Many researchers have integrated MOFs with other classes of materials to produce new structures with synergetic properties. Despite there being over 70,000 collections of synthesized MOFs that can be used as building blocks, the precise nature of the interaction and the bonding at the interface between the two materials still remains unknown. The question is how to sort out the right matching pairs out of 70,000 MOFs. An algorithmic study published in Nature Communications by a KAIST research team presents a clue for finding the perfect pairs. The team, led by Professor Ji-Han Kim from the Department of Chemical and Biomolecular Engineering, developed a joint computational and experimental approach to rationally design MOF＠MOFs, a composite of MOFs where an MOF is grown on a different MOF. Professor Kim’s team, in collaboration with UNIST, noted that the metal node of one MOF can coordinately bond with the linker of a different MOF and the precisely matched interface configurations at atomic and molecular levels can enhance the likelihood of synthesizing MOF＠MOFs. They screened thousands of MOFs and identified optimal MOF pairs that can seamlessly connect to one another by taking advantage of the fact that the metal node of one MOF can form coordination bonds with the linkers of the second MOF. Six pairs predicted from the computational algorithm successfully grew into single crystals. This computational workflow can readily extend into other classes of materials and can lead to the rapid exploration of the composite MOFs arena for accelerated materials development. Even more, the workflow can enhance the likelihood of synthesizing MOF＠MOFs in the form of large single crystals, and thereby demonstrated the utility of rationally designing the MOF＠MOFs. This study is the first algorithm for predicting the synthesis of composite MOFs, to the best of their knowledge. Professor Kim said, “The number of predicted pairs can increase even more with the more general 2D lattice matching, and it is worth investigating in the future.” This study was supported by Samsung Research Funding & Incubation Center of Samsung Electronics. (Figure: An example of a rationally synthesized  MOF＠MOFs (cubic HKUST-1＠MOF-5 ))

Enhanced Natural Gas Storage to Help Reduce Global..

  < Professor Atilhan (left) and Professor Yavuz (right) >   Researchers have designed plastic-based materials that can store natural gas more effectively. These new materials can not only make large-scale, cost-effective, and safe natural gas storage possible, but further hold a strong promise for combating global warming.   Natural gas (predominantly methane) is a clean energy alternative. It is stored by compression, liquefaction, or adsorption. Among these, adsorbed natural gas (ANG) storage is a more efficient, cheaper, and safer alternative to conventional compressed natural gas (CNG) and liquefied natural gas (LNG) storage approaches that have drawbacks such as low storage efficiency, high costs, and safety concerns. However, developing adsorptive materials that can more fully exploit the advantages of ANG storage has remained a challenging task.   A KAIST research team led by Professor Cafer T. Yavuz from the Graduate School of Energy, Environment, Water, and Sustainability (EEWS), in collaboration with Professor Mert Atilhan’s group from Texas A&M University, synthesized 29 unique porous polymeric structures with inherent flexibility, and tested their methane gas uptake capacity at high pressures. These porous polymers had varying synthetic complexities, porosities, and morphologies, and the researchers subjected each porous polymer to pure methane gas under various conditions to study the ANG performances.   Of these 29 distinct chemical structures, COP-150 was particularly noteworthy as it achieved a high deliverable gravimetric methane working capacity when cycled between 5 and 100 bar at 273 K, which is 98％ of the total uptake capacity. This result surpassed the target set by the United States Department of Energy (US DOE).   COP-150 is the first ever structure to fulfil both the gravimetric and volumetric requirements of the US DOE for successful vehicular use, and the total cost to produce the COP-150 adsorbent was only 1 USD per kilogram.   COP-150 can be produced using freely available and easily accessible plastic materials, and moreover, its synthesis takes place at room temperature, open to the air, and no previous purification of the chemicals is required. The pressure-triggered flexible structure of COP-150 is also advantageous in terms of the total working capacity of deliverable methane for real applications.   The research team believed that the increased pressure flexes the network structure of COP-150 showing “swelling” behavior, and suggested that the flexibility provides rapid desorption and thermal management, while the hydrophobicity and the nature of the covalently bonded framework allow these promising materials to tolerate harsh conditions.   This swelling mechanism of expansion-contraction solves two other major issues, the team noted. Firstly, when using adsorbents based on such a mechanism, unsafe pressure spikes that may occur due to temperature swings can be eliminated. In addition, contamination can also be minimized, since the adsorbent remains contracted when no gas is stored.   Professor Yavuz said, “We envision a whole host of new designs and mechanisms to be developed based on our concept. Since natural gas is a much cleaner fuel than coal and petroleum, new developments in this realm will help switching to the use of less polluting fuels.”   Professor Atilhan agreed the most important impact of their research is on the environment. “Using natural gas more than coal and petroleum will significantly reduce greenhouse gas emissions. We believe, one day, we might see vehicles equipped with our materials that are run by a cleaner natural gas fuel,” he added.   This study, reported in Nature Energy on July 8, was supported by National Research Foundation of Korea (NRF) grants ( NRF-2016R1A2B4011027, NRF-2017M3A7B4042140, and NRF-2017M3A7B4042235).       < Suggested chemical structure of COP-150 >     < Initial ingredients (left) and final product (right) of COP-150 synthesis >   < Comparison of highest reported volumetric working capacities >

Highly Uniform and Low Hysteresis Pressure Sensor ..

< Professor Steve Park (left) and the First Author Mr. Jinwon Oh (right) >   Researchers have designed a flexible pressure sensor that is expected to have a much wider applicability. A KAIST research team fabricated a piezoresistive pressure sensor of high uniformity with low hysteresis by chemically grafting a conductive polymer onto a porous elastomer template.   The team discovered that the uniformity of pore size and shape is directly related to the uniformity of the sensor. The team noted that by increasing pore size and shape variability, the variability of the sensor characteristics also increases.   Researchers led by Professor Steve Park from the Department of Materials Science and Engineering confirmed that compared to other sensors composed of randomly sized and shaped pores, which had a coefficient of variation in relative resistance change of 69.65％, their newly developed sensor exhibited much higher uniformity with a coefficient of variation of 2.43％. This study was reported in Small as the cover article on August 16.   Flexible pressure sensors have been actively researched and widely applied in electronic equipment such as touch screens, robots, wearable healthcare devices, electronic skin, and human-machine interfaces. In particular, piezoresistive pressure sensors based on elastomer‐conductive material composites hold significant potential due to their many advantages including a simple and low-cost fabrication process.   Various research results have been reported for ways to improve the performance of piezoresistive pressure sensors, most of which have been focused on increasing the sensitivity. Despite its significance, maximizing the sensitivity of composite-based piezoresistive pressure sensors is not necessary for many applications. On the other hand, sensor-to-sensor uniformity and hysteresis are two properties that are of critical importance to realize any application.   The importance of sensor-to-sensor uniformity is obvious. If the sensors manufactured under the same conditions have different properties, measurement reliability is compromised, and therefore the sensor cannot be used in a practical setting.   In addition, low hysteresis is also essential for improved measurement reliability. Hysteresis is a phenomenon in which the electrical readings differ depending on how fast or slow the sensor is being pressed, whether pressure is being released or applied, and how long and to what degree the sensor has been pressed. When a sensor has high hysteresis, the electrical readings will differ even under the same pressure, making the measurements unreliable.   Researchers said they observed a negligible hysteresis degree which was only 2％. This was attributed to the strong chemical bonding between the conductive polymer and the elastomer template, which prevents their relative sliding and displacement, and the porosity of the elastomer that enhances elastic behavior.   “This technology brings forth insight into how to address the two critical issues in pressure sensors: uniformity and hysteresis. We expect our technology to play an important role in increasing practical applications and the commercialization of pressure sensors in the near future,” said Professor Park.   This work was conducted as part of the KAIST‐funded Global Singularity Research Program for 2019, and also supported by the KUSTAR‐KAIST Institute.    Figure 1. Image of a porous elastomer template with uniform pore size and shape (left), Graph showing high uniformity in the sensors’ performance (right).   Figure 2. Hysteresis loops of the sensor at different pressure levels (left), and after a different number of cycles (right).    Figure 3. The cover page of Small Journal, Volume 15, Issue 33   Publication: Jinwon Oh, Jin‐Oh Kim, Yunjoo Kim, Han Byul Choi, Jun Chang Yang, Serin Lee, Mikhail Pyatykh, Jung Kim, Joo Yong Sim, and Steve Park. 2019. Highly Uniform and Low Hysteresis Piezoresistive Pressure Sensors Based on Chemical Grafting of Polypyrrole on Elastomer Template with Uniform Pore Size. Small. Wiley-VCH Verlag GmbH & Co. KgaA, Weinheim, Germany, Volume No. 15, Issue No. 33, Full Paper No. 201901744, 8 pages. https://doi.org/10.1002/smll.201901744   Profile: Prof. Steve Park, MS, PhD stevepark＠kaist.ac.kr http://steveparklab.kaist.ac.kr/ Assistant Professor Organic and Nano Electronics Laboratory Department of Materials Science and Engineering Korea Advanced Institute of Science and Technology (KAIST) http://kaist.ac.kr Daejeon 34141, Korea   Profile: Mr. Jinwon Oh, MS jwoh1701＠gmail.com http://steveparklab.kaist.ac.kr/ Researcher Organic and Nano Electronics Laboratory Department of Materials Science and Engineering Korea Advanced Institute of Science and Technology (KAIST) http://kaist.ac.kr Daejeon 34141, Korea   Profile: Prof. Jung Kim, MS, PhD jungkim＠kaist.ac.kr http://medev.kaist.ac.kr/ Professor Biorobotics Laboratory Department of Mechanical Engineering Korea Advanced Institute of Science and Technology (KAIST) http://kaist.ac.kr Daejeon 34141, Korea   Profile: Joo Yong Sim, PhD jsim＠etri.re.kr Researcher Bio-Medical IT Convergence Research Department Electronics and Telecommunications Research Institute (ETRI) https://www.etri.re.kr Daejeon 34129, Korea      (END)

Manipulating Brain Cells by Smartphone

Researchers have developed a soft neural implant that can be wirelessly controlled using a smartphone. It is the first wireless neural device capable of indefinitely delivering multiple drugs and multiple colour lights, which neuroscientists believe can speed up efforts to uncover brain diseases such as Parkinson’s, Alzheimer’s, addiction, depression, and pain.   A team under Professor Jae-Woong Jeong from the School of Electrical Engineering at KAIST and his collaborators have invented a device that can control neural circuits using a tiny brain implant controlled by a smartphone. The device, using Lego-like replaceable drug cartridges and powerful, low-energy Bluetooth, can target specific neurons of interest using drugs and light for prolonged periods. This study was published in Nature Biomedical Engineering. “This novel device is the fruit of advanced electronics design and powerful micro and nanoscale engineering,” explained Professor Jeong. “We are interested in further developing this technology to make a brain implant for clinical applications.” This technology significantly overshadows the conventional methods used by neuroscientists, which usually involve rigid metal tubes and optical fibers to deliver drugs and light. Apart from limiting the subject’s movement due to bulky equipment, their relatively rigid structure causes lesions in soft brain tissue over time, therefore making them not suitable for long-term implantation. Although some efforts have been made to partly mitigate adverse tissue response by incorporating soft probes and wireless platforms, the previous solutions were limited by their inability to deliver drugs for long periods of time as well as their bulky and complex control setups. To achieve chronic wireless drug delivery, scientists had to solve the critical challenge of the exhaustion and evaporation of drugs. To combat this, the researchers invented a neural device with a replaceable drug cartridge, which could allow neuroscientists to study the same brain circuits for several months without worrying about running out of drugs. These ‘plug-n-play’ drug cartridges were assembled into a brain implant for mice with a soft and ultrathin probe (with the thickness of a human hair), which consisted of microfluidic channels and tiny LEDs (smaller than a grain of salt), for unlimited drug doses and light delivery. Controlled with an elegant and simple user interface on a smartphone, neuroscientists can easily trigger any specific combination or precise sequencing of light and drug delivery in any implanted target animal without the need to be physically inside the laboratory. Using these wireless neural devices, researchers can also easily setup fully automated animal studies where the behaviour of one animal could affect other animals by triggering light and/or drug delivery. “The wireless neural device enables chronic chemical and optical neuromodulation that has never been achieved before,” said lead author Raza Qazi, a researcher with KAIST and the University of Colorado Boulder. This work was supported by grants from the National Research Foundation of Korea, US National Institute of Health, National Institute on Drug Abuse, and Mallinckrodt Professorship.         (A neural implant with replaceable drug cartridges and Bluetooth low-energy can target specific neurons.)        (Micro LED controlling using smartphone application)

[AZoNano] New Strategy for Synthesizing Single-Cry..

A group of researchers from KAIST has developed a new approach for producing single-crystalline graphene quantum dots, which release stable blue light.    

    Uniformly ordered single-crystalline graphene quantum dots of various sizes synthesized through solution chemistry. (Image credit: KAIST)   The scientists verified that a display built using their synthesized graphene quantum dots effectively released blue light with stable electric pressure, apparently resolving the persistent problems faced in achieving blue light emission in manufactured displays. The research, headed by Professor O Ok Park from the Department of Chemical and Biological Engineering, appeared online in Nano Letters on July 5th, 2019. Graphene has won increased interest as a next-generation material for its electrical and heat conductivity and also its transparency. However, single- and multi-layered graphene have characteristics of a conductor hence it is not easy to be applied into a semiconductor. The semiconductor’s unique characteristic of bandgap will be shown to release the light in the graphene only upon being downsized to the nanoscale. This illuminating featuring of dot is known as a graphene quantum dot.   Traditionally, single-crystalline graphene has been produced by chemical vapor deposition (CVD) on nickel or copper thin films, or by peeling graphite chemically and physically. However, graphene produced through chemical vapor deposition is principally employed for large-surface transparent electrodes. However, graphene fabricated by chemical and physical peeling has irregular size defects.   The group of scientists described that their graphene quantum dots showed a highly stable single-phase reaction when they combined amine and acetic acid with an aqueous solution of glucose. After that, they produced single-crystalline graphene quantum dots through the self-assembly of the reaction intermediate. During fabrication, the group created a new separation technique at a low-temperature precipitation, which resulted in the successful production of homogeneous nucleation of graphene quantum dots through a single-phase reaction. Professor Park and his teammates have created solution-phase synthesis technology that enables the construction of the desired crystal size for single nanocrystals down to 100 nm. It is supposedly the first production of the homogeneous nucleation of graphene through a single-phase reaction.   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. Professor O Ok Park, Department of Chemical and Biological Engineering, KAIST   This study was a joint project with a group from Korea University under Professor Sang Hyuk Im at 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. Source: https://www.kaist.ac.kr/html/en/index.html  

[Electronics Online] A powerful tool to analyze MO..

An international team, including staff from the Korea Advanced Institute of Science and Technology (Kaist; Daejeon, South Korea; www.kaist.ac.kr), led by Kaist’s professor Jeung Ku Kang, has developed a technology to analyze the gas adsorption behavior of molecules of each individual pore of a metal organic framework (MOF). Existing technology is only able to measure the amount of gas molecules adsorbed by the material, without directly observing the adsorption behavior.   The team developed a realtime gas-adsorption crystallography system by integrating an existing X-ray diffraction measurement device that can provide structural information and a gas adsorption measurement device. The system allows the observation of a mesoporous MOF with multiple pores. The team categorized the adsorption behavior of MOF molecules by pore type, achieving the identification of a stepwise adsorption process that was not previously possible to analyze.   The team analyzed how the pore structure and the type of adsorption molecule affect the adsorption behavior to suggest what type of MOF structure is suitable as a storage material for each type of adsorption behavior. Specifically, the team used two MOFs, PCN-224 and ZIF-412 which contain two and three different types of pore, respectively, to generate isotherms of individual pores by combining gas adsorption measurements with in situ X-ray diffraction.   This isotherm decomposition approach provides access to information about the gas uptake capacity, surface area and accessible pore volume of each individual pore, as well as the impact of pore geometry on the uptake and distribution of different adsorbates within the pores.   “By understanding the realtime adsorption behavior of molecules at the level of the pores that form the material, rather than the whole material, we will be able to apply this technology to develop a new high-capacity storage material,” says professor Kang.   https://www.chemengonline.com/powerful-tool-analyze-mofs/?printmode=1

Researchers Describe a Mechanism Inducing Self-Kil..

 (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.  

Synthesizing Single-Crystalline Hexagonal Graphene..

                                 (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.

‘Flying Drones for Rescue’

        < Team USRG and Professor Shim (second from the right) >   Having recently won the AI R&D Grand Challenge Competition in Korea with their drone, 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.”