본문 바로가기
대메뉴 바로가기
KAIST
Newsletter Vol.25
Receive KAIST news by email!
View
Subscribe
Close
Type your e-mail address here.
Subscribe
Close
KAIST
NEWS
유틸열기
홈페이지 통합검색
-
검색
KOREAN
메뉴 열기
DAP
by recently order
by view order
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 10755
Study of T Cells from COVID-19 Convalescents Guides Vaccine Strategies
Researchers confirm that most COVID-19 patients in their convalescent stage carry stem cell-like memory T cells for months A KAIST immunology research team found that most convalescent patients of COVID-19 develop and maintain T cell memory for over 10 months regardless of the severity of their symptoms. In addition, memory T cells proliferate rapidly after encountering their cognate antigen and accomplish their multifunctional roles. This study provides new insights for effective vaccine strategies against COVID-19, considering the self-renewal capacity and multipotency of memory T cells. COVID-19 is a disease caused by severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) infection. When patients recover from COVID-19, SARS-CoV-2-specific adaptive immune memory is developed. The adaptive immune system consists of two principal components: B cells that produce antibodies and T cells that eliminate infected cells. The current results suggest that the protective immune function of memory T cells will be implemented upon re-exposure to SARS-CoV-2. Recently, the role of memory T cells against SARS-CoV-2 has been gaining attention as neutralizing antibodies wane after recovery. Although memory T cells cannot prevent the infection itself, they play a central role in preventing the severe progression of COVID-19. However, the longevity and functional maintenance of SARS-CoV-2-specific memory T cells remain unknown. Professor Eui-Cheol Shin and his collaborators investigated the characteristics and functions of stem cell-like memory T cells, which are expected to play a crucial role in long-term immunity. Researchers analyzed the generation of stem cell-like memory T cells and multi-cytokine producing polyfunctional memory T cells, using cutting-edge immunological techniques. This research is significant in that revealing the long-term immunity of COVID-19 convalescent patients provides an indicator regarding the long-term persistence of T cell immunity, one of the main goals of future vaccine development, as well as evaluating the long-term efficacy of currently available COVID-19 vaccines. The research team is presently conducting a follow-up study to identify the memory T cell formation and functional characteristics of those who received COVID-19 vaccines, and to understand the immunological effect of COVID-19 vaccines by comparing the characteristics of memory T cells from vaccinated individuals with those of COVID-19 convalescent patients. PhD candidate Jae Hyung Jung and Dr. Min-Seok Rha, a clinical fellow at Yonsei Severance Hospital, who led the study together explained, “Our analysis will enhance the understanding of COVID-19 immunity and establish an index for COVID-19 vaccine-induced memory T cells.” “This study is the world’s longest longitudinal study on differentiation and functions of memory T cells among COVID-19 convalescent patients. The research on the temporal dynamics of immune responses has laid the groundwork for building a strategy for next-generation vaccine development,” Professor Shin added. This work was supported by the Samsung Science and Technology Foundation and KAIST, and was published in Nature Communications on June 30. -Publication: Jung, J.H., Rha, MS., Sa, M. et al. SARS-CoV-2-specific T cell memory is sustained in COVID-19 convalescent patients for 10 months with successful development of stem cell-like memory T cells. Nat Communications 12, 4043 (2021). https://doi.org/10.1038/s41467-021-24377-1 -Profile: Professor Eui-Cheol Shin Laboratory of Immunology & Infectious Diseases (http://liid.kaist.ac.kr/) Graduate School of Medical Science and Engineering KAIST
2021.07.05
View 9742
Anti-drone Technology for Anti-Terrorism Applications
(from top right clockwise: Professor Yongdae Kim, PhD Candidates Yujin Kwon, Juhwan Noh, Hocheol Shin, and Dohyun Kim) KAIST researchers have developed anti-drone technology that can hijack other drones by spoofing its location using fake GPS signals. This technology can safely guide a drone to a desired location without any sudden change in direction in emergency situations, and thus respond effectively to dangerous drones such as those intending to carry out acts of terrorism. Advancements in the drone industry have led to the wider use of drones in our daily lives in areas of reconnaissance, searching and rescuing, disaster prevention and response, and delivery services. At the same time, there has also been a growing concern about privacy, safety, and security issues regarding drones, especially those arising from intrusion into private property and secure facilities. Therefore, the anti-drone industry is rapidly expanding to detect and respond to this possible drone invasion. The current anti-drone systems used in airports and other key locations utilize electronic jamming signals, high-power lasers, or nets to neutralize drones. For example, drones trespassing on airports are often countered with simple jamming signals that can prevent the drones from moving and changing position, but this may result in a prolonged delay in flight departures and arrivals at the airports. Drones used for terrorist attacks – armed with explosives or weapons – must also be neutralized a safe distance from the public and vital infrastructure to minimize any damage. Due to this need for a new anti-drone technology to counter these threats, a KAIST research team led by Professor Yongdae Kim from the School of Electrical Engineering has developed technology that securely thwarts drones by tricking them with fake GPS signals. Fake GPS signals have been used in previous studies to cause confusion inside the drone regarding its location, making the drone drift from its position or path. However, such attack tactics cannot be applied in GPS safety mode. GPS safety mode is an emergency mode that ensures drone safety when the signal is cut or location accuracy is low due to a fake GPS signals. This mode differs between models and manufacturers. Professor Kim’s team analyzed the GPS safety mode of different drone models made from major drone manufacturers such as DJI and Parrot, made classification systems, and designed a drone abduction technique that covers almost all the types of drone GPS safety modes, and is universally applicable to any drone that uses GPS regardless of model or manufacturer. The research team applied their new technique to four different drones and have proven that the drones can be safely hijacked and guided to the direction of intentional abduction within a small margin of error. Professor Kim said, “Conventional consumer drones equipped with GPS safety mode seem to be safe from fake GPS signals, however, most of these drones are able to be detoured since they detect GPS errors in a rudimentary manner.” He continued, “This technology can contribute particularly to reducing damage to airports and the airline industry caused by illegal drone flights.” The research team is planning to commercialize the developed technology by applying it to existing anti-drone solutions through technology transfer.” This research, featured in the ACM Transactions on Privacy and Security (TOPS) on April 9, was supported by the Defense Acquisition Program Administration (DAPA) and the Agency for Defense Development (ADD). Image 1. Experimental environment in which a fake GPS signal was produced from a PC and injected into the drone signal using directional antennae Publication: Juhwan Noh, Yujin Kwon, Yunmok Son, Hocheol Shin, Dohyun Kim, Jaeyeong Choi, and Yongdae Kim. 2019. Tractor Beam: Safe-hijacking of Consumer Drones with Adaptive GPS Spoofing. ACM Transactions on Privacy and Security. New York, NY, USA, Vol. 22, No. 2, Article 12, 26 pages. https://doi.org/10.1145/3309735 Profile: Prof. Yongdae Kim, MS, PhD yongdaek@kaist.ac.kr https://www.syssec.kr/ Professor School of Electrical Engineering Korea Advanced Institute of Science and Technology (KAIST) http://kaist.ac.kr Daejeon 34141, Korea Profile: Juhwan Noh, PhD Candidate juhwan@kaist.ac.kr PhD Candidate System Security (SysSec) Lab School of Electrical Engineering Korea Advanced Institute of Science and Technology (KAIST) http://kaist.ac.kr Daejeon 34141, Korea (END)
2019.06.25
View 41785
Strengthening Industry-Academia Cooperation with LG CNS
On November 20, KAIST signed an MoU with LG CNS for industry-academia partnership in education, research, and business in the fields of AI and Big Data. Rather than simply developing education programs or supporting industry-academia scholarships, both organizations agreed to carry out a joint research project on AI and Big Data that can be applied to practical business. KAIST will collaborate with LG CNS in the fields of smart factories, customer analysis, and supply chain management analysis. Not only will LG CNS offer internships to KAIST students, but it also will support professors and students who propose innovative startup ideas for AI and Big Data. Offering an industry-academia scholarship for graduate students is also being discussed. Together with LG CNS, KAIST will put its efforts into propose projects regarding AI and Big Data in the public sector. Furthermore, KAIST and LG CNS will jointly explore and carry out industry-academia projects that could be practically used in business. Both will carry out the project vigorously through strong cooperation; for instance, LG CNS employees can be assigned to KAIST, if necessary. Also, LG CNS’s AI and Big Data platform, called DAP (Data Analytics & AI Platform) will be used as a data analysis tool during the project and the joint outcomes will be installed in DAP. KAIST professors with expertise in AI deep learning have trained LG CNS employees since the Department of Industrial & Systems Engineering established ‘KAIST AI Academy’ in LG CNS last August. “With KAIST, the best research-centered university in Korea, we will continue to lead in developing the field of AI and Big Data and provide innovative services that create value by connecting them to customer business,” Yong Shub Kim, the CEO of LG CNS, highlighted.
2017.11.22
View 9109
<<
첫번째페이지
<
이전 페이지
1
>
다음 페이지
>>
마지막 페이지 1