Fundamental technology
We are building an open innovation platform for industry, academia, and government.
Proposing new technology that supports and understands living scenarios
Situational understanding under various environments such as manufacturing workplaces, service industry workplaces, and the home is needed as a fundamental technology in the pursuit of coexistence of humans and machines. So AIRC is putting effort into research of 3D object recognition, movement recognition, and environment recognition.
Specifically, we are constructing 3D data of objects found in daily life and movement data of people, and proposing technology that comprehends and supports living scenarios. In addition, for the future we are exploring methods to apply this data to robot behavior planning.
In this field, we have established technology using deep learning that recognizes both shapes and functions of objects from 3D data. In addition, we have built a cloud-based virtual reality (VR) environment and are accumulating huge amounts of interaction data between humans and robots.
Specifically, we are constructing 3D data of objects found in daily life and movement data of people, and proposing technology that comprehends and supports living scenarios. In addition, for the future we are exploring methods to apply this data to robot behavior planning.
In this field, we have established technology using deep learning that recognizes both shapes and functions of objects from 3D data. In addition, we have built a cloud-based virtual reality (VR) environment and are accumulating huge amounts of interaction data between humans and robots.
-
Theme1Interactive robots based on cloud-based VR
By building a cloud-based VR environment, a large-scale, long-duration interaction experiments using crowd sourcing have become possible. We are building a framework in which hundreds of people simultaneously participate in a 10,000-hour interaction experience, from which data can be accumulated and shared on the cloud. -
-
Theme2Object recognition technology using deep learning
We have successfully developed new object recognition technology using deep learning technology that surpasses the accuracy of conventional methods while using only a small number of observed images. We won first place worldwide in the international 3D object retrieval competition SHREC 2017 for an algorithm developed for this research topic. -