The University of Tokyo · 컴퓨터과학
Tatsuya Matsushima 교수의 연구실은 실생활 응용에 적합한 로봇 시스템 개발에 초점을 맞추고 있으며, 특히 헬스케어, 교육, 대화형 에이전트, 로봇 제어 등에서의 안전하고 효율적인 강화학습 및 메타학습 기반 학습 기법을 연구합니다. 데이터 기반의 유연한 시스템 설계를 통해 복잡하고 변동성이 큰 환경에서도 안정적으로 동작하는 서비스 로봇의 구현을 목표로 하며, 실제 도메인에서의 성능 검증과 실용성 확보를 중시합니다. 특히, 배포 빈도를 최소화하면서도 높은 성능을 달성하는 '배포 효율성' 개념 도입 등 실용적 제약을 고려한 학습 프레임워크 개발에 기여하고 있습니다.
표시된 성과는 수집된 데이터 기준으로 산출되며, 일부 차이가 있을 수 있습니다.
Most reinforcement learning (RL) algorithms assume online access to the environment, in which one may readily interleave updates to the policy with experience collection using that policy. However, in many real-world applications such as health, education, dialogue agents, and robotics, the cost or potential risk of deploying a new data-collection policy is high, to the point that it can become prohibitive to update the data-collection policy more than a few times during learning. With this view
Tidying up a household environment using a mobile manipulator poses various challenges in robotics, such as adaptation to large real-world environmental variations, and safe and robust deployment in the presence of humans. The Partner Robot Challenge in World Robot Challenge (WRC) 2020, a global competition held in September 2021, benchmarked tidying tasks in real home environments, and, importantly, tested for full system performances. For this challenge, we developed an entire household servic
Most reinforcement learning (RL) algorithms assume online access to the environment, in which one may readily interleave updates to the policy with experience collection using that policy. However, in many real-world applications such as health, education, dialogue agents, and robotics, the cost or potential risk of deploying a new data-collection policy is high, to the point that it can become prohibitive to update the data-collection policy more than a few times during learning. With this view
To endow robots with the flexibility to perform a wide range of tasks in diverse and complex environments, learning their controller from experience data is a promising approach. In particular, some recent meta-learning methods are shown to solve novel tasks by leveraging their experience of performing other tasks during training. Although studies around meta-learning of robot control have worked on improving the performance, the safety issue has not been fully explored, which is also an importa
Tidying up a household environment using a mobile manipulator poses various challenges in robotics, such as adaptation to large real-world environmental variations, and safe and robust deployment in the presence of humans.The Partner Robot Challenge in World Robot Challenge (WRC) 2020, a global competition held in September 2021, benchmarked tidying tasks in the real home environments, and importantly, tested for full system performances.For this challenge, we developed an entire household servi
Service robot systems, especially household robot systems, have recently achieved adaptability in various environments and tasks by leveraging some machine learning modules. In developing and verifying such data-driven robotic systems, not only the hardware, programs, and communications but also the data and models used are components to be considered. This paper discusses effective data-driven development processes for such service robot systems by introducing and discussing case studies from t
