대구경북과학기술원
전기전자컴퓨터공학과박대희 교수
- Data-driven Decision Making in Autonomous Systems: A Prediction and Planning Perspective
Recent advances in AI for autonomous systems have largely focused on the perception stage of the decision-making pipeline.
While perception technologies such as object detection and semantic segmentation have made remarkable progress, they are not sufficient for optimal decision making in dynamic and uncertain environments. To ensure safe and effective operation, autonomous systems must also excel at prediction—forecasting the future behavior of agents—and planning—generating goal-directed, adaptive actions. However, challenges such as data sparsity, uncertainty in long-tail scenarios, and misalignment between prediction and planning still remain. In this talk, I will introduce recent advances in learning-based prediction and planning, and discuss how integrated frameworks and task-specific representations can help bridge the gap between these two components, ultimately enabling more robust and intelligent autonomous decision making.
경북대학교
컴퓨터학부이재협 교수
- 인공지능 기반 위성 영상 복원 및 활용 연구
인공지능 기반 위성 영상 복원 및 활용 연구에 대한 소개를 진행한다. 전체 소개는 위성 영상 품질 복원 연구, 위성 레이더 영상으로부터 광학 영상으로의 변환 연구 및 객체 탐지 연구에 대한 발표를 진행하며, 소개 연구는 TGRS, CVPR에 게재 및 발표 예정인 연구 논문을 기반으로 소개를 진행한다. 위성 레이더 영상으로부터 광학 영상으로의 변환 연구, 위성 광학 영상의 품질 개선을 위한 영상 복원 연구, 위성 영상 객체 탐지 연구 등을 소개한다.
계명대학교 의용공학과
이종하 교수
- Remote Biosignal Sensing for Emotional Intelligence
The measurement of vital signs such as blood pressure plays a key role in human health. Usually, we encounter some problems when we check them in the traditional way; for example, it is impossible to check continuously, and measuring vital signs requires direct contact with the patient, which can be uncomfortable for certain individuals. In this research, we present a vision-based system for estimating blood pressure using pulse transit time (PTT) and the Eulerian video magnification (EVM) technique to amplify tiny color variations caused by blood flow to calculate arterial pulse waves traveling between two arterial sites. Calculating the PTT by processing the video signal for each subject, an oscillometer BP device was used to evaluate the performance between measurements in different conditions, including rest, exercise, and during recovery. Mean systolic BP was 115 mmHg at rest, 137 mmHg during high-intensity exercise, and 114 mmHg during recovery, respectively. The average value of diastolic blood pressure did not change significantly before, during, and after exercise. When we compared the systolic and diastolic blood pressure with ground-truth results, our system showed an accuracy of 91% for systolic blood pressure and 90% for diastolic blood pressure.