기계·로봇 연구정보센터에서 매달 온라인 세미나를 개최하고 있습니다. 

웨비나는 참여 신청 후 누구나 부담없이 해당일에 참여 가능합니다 .  
관심있는 모든 분들의 참여를 부탁드립니다. ^^

*참여하셔서 질문해주시면 커피쿠폰을 보내드립니다.  
(웹캠이나 마이크 없어도 가능, 모바일 가능, 채팅으로 질의 응답가능)

2021.06 전체 웨비나 일정 보러가기

1. 게임이론을 활용한 자율주행자동차의 판단/제어 전략​ - 한경석 교수(경북대학교 기계공학부)​

일시: 2021-06-25(금) 오후 3시(발표 45분 / 토론, 질의응답 15분)

요약: 최근 자율주행관련 연구가 활발하지만 완전 자율주행시대에 도달할 수 있을지는 누구도 확신할 수 없다. 하지만, 사람이 운전하는 차량과 자율주행차가 도로내에 혼재하는 과도기를 겪게 되는데 주변 차량의 주행의도를 파악하여 적합한 판단/제어를 할 수 있어야만 안전한 자율주행이 가능하다. 본 웨비나에서는 게임이론에 기반하여 실시간 인간-로봇(자율차)의 상호작용을 고려한 자율차의 판단/제어알고리즘 개발에 관련된 내용을 발표한다.

웨비나 참여 신청:  게임이론을 활용한 자율주행자동차의 판단/제어 전략 ​ 웨비나 신청하러 가기

2. Designing intelligent mobile-manipulation robots​​ - 김범준 교수(KAIST AI 대학원)​

일시: 2021-06-28(월) 오후 2시(발표 45분 / 토론, 질의응답 15분)

요약: How can we enable robots to efficiently reason both at discrete task-level and continuous motion-level to achieve high-level goals such as tidying up a room or constructing a building? This is a challenging problem that requires integrated reasoning about the combinatoric aspects, such as deciding which object to manipulate, and feasibility of each motion, such as collision-free constraints, to achieve goals.  The classical robotics approach is to design a planner, that, given an initial state, goal, and transition model, computes a plan. The advantage of such a pure-planning approach is the immense generalization capability: for any given state and goal, the planner will find the solution if there is one. The inherent drawback, however, is that the planners do not typically make use of planning experience, and compute a plan from scratch every time it encounters a new problem. For complex problems, this renders them extremely inefficient. Alternatively, we can take a pure-learning approach where you learn, from either reinforcement signals or demonstrations, a policy that maps a state to an action to execute. The advantage here is that computing the next action to execute becomes much cheaper than pure planning because it comes down to making a prediction from a function approximator. The drawback, however, is that it is brittle. If the policy encounters a state that is very different from the ones seen in the training set, then it is likely to make mistakes and might get into a situation where it would not know how to proceed. My approach is to take the middle-ground between these two extremes to achieve the best of both worlds. More concretely, in this talk, I will introduce several algorithms that learn to guide a planner from planning experience. I will describe state representations, neural network architectures, and data-efficient learning algorithms. Our methods learn to perform combinatoric reasoning in the task-level planning and feasibility reasoning in the motion-level planning using a function approximator to guide a planner. Lastly, I will present a planning algorithm that balances the exploitation of the learned knowledge and exploration of new choices in a principled manner.​

웨비나 참여 신청:  Designing intelligent mobile-manipulation robots 웨비나 신청하러 가기

3. 실내외 구조적 패턴을 활용한 영상 기반 항법 연구 동향 - 김표진 교수(숙명여대 기계시스템학부)​

• 웨비나
• 웹세미나
• 기계로봇
• 게임이론
• 자율주행