http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Prediction of pedestrian trajectory based on long short-term memory of data
Tomoya On,Takashi Kanamaru 제어로봇시스템학회 2021 제어로봇시스템학회 국제학술대회 논문집 Vol.2021 No.10
Recently, development of navigation robots and autonomous cars are rapidly progressing. When such robots become popular in our daily life, their collisions with humans should be avoided for safety. For that purpose, we predict pedestrian trajectories with LSTM (long short-term memory) networks and conventional neural networks, and we compare their results. In order to predict sequential data, we use the following two methods: (I) predicting steps of data with models, and (II) predicting steps of data with a model by applying one-step prediction several times. By examining these two methods, it was found that the performances of the method I with the LSTM network and the conventional neural network are comparable, and the performance of the method II with the LSTM network is significantly better than that with the conventional neural network.
Development of drinking support device for spinal cord injuries to enhance quality of life
Ayano Tanishima,Takashi Nakakuki,Hiroto Noguchi,Takashi Kanamaru 제어로봇시스템학회 2013 제어로봇시스템학회 국제학술대회 논문집 Vol.2013 No.10
Spinal cord injury causes a paralysis of any part of the body depending on which part of spinal cord is destroyed. It is well known that a severity of the paralysis is determined by both a location and a degree of injury in the vertebral bones. For example, in a case of injury at the C4 vertebral bone a patient is paralyzed from the neck down, and needs a caregiver to help almost all activities of daily life. Recently, a quality of life is considered to be important, and various welfare devices have been proposed to realize a better life of a patient. Regarding a C4 patient, drinking water by oneself whenever he/she wants to do is strongly desired in the daily life. In this paper, we develop a drinking support device for a C4 patient. The device is evaluated in a rehabilitation hospital, and it is shown that all requirements on structure, degree of freedom, safety, conform, daily maintenance, etc. are satisfied with an acceptable level.
Developing Education Support System using Interactive Floor Interface
Tomoya Ono,Soshi Akasaka,Hiroki Ohara,Takashi Kanamaru 제어로봇시스템학회 2020 제어로봇시스템학회 국제학술대회 논문집 Vol.2020 No.10
Recently, ICT equipment has been introduced to classrooms in Japan. Moreover, effectiveness of active learning that engages students as active participants in their learning has been discussed. In order to merge the usefulness of ICT and the effectiveness of active learning, we developed interactive floor interface (IFI) that enables users to see teaching materials displayed on a floor and to control it with their gestures. We also developed an interactive teaching material of wave interference designed for IFI. To confirm the effectiveness of IFI, we gave examinations before and after learning to two groups each of which learns wave interference by using either a usual textbook or IFI. As a result, it was found that average scores of examinations have significantly increased in both groups. Although an average increase of scores for IFI was higher than that of usual textbook, we could not show its significant difference. It is important to improve teaching materials for IFI by giving further interactivity, user-friendliness, and so on.