1
views
0
recommends
+1 Recommend
1 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Overview of the five key research groups within the Behaviour Signal Processing Laboratory (Takeda Laboratory) at Nagoya University

      Impact

      Science Impact, Ltd.

      Read this article at

      ScienceOpenPublisher
      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          The Takeda Laboratory, led by Professor Kazuya Takeda, is part of the Graduate School of Informatics at Nagoya University in Japan. Takeda says: 'Our laboratory focuses on applying digital signal processing (DSP) technologies to a variety of problems that arise from the interaction of humans with the rest of the world.' The large team, comprising almost 40 professors, postdoctoral researchers, postgraduates and undergraduates, focus on DSP in the fields of music, acoustics, speech and language, and driverless vehicles. Takeda says: 'Our findings have led to new products to enhance virtual reality experiences, created new ways for musicians to compose and for listeners to enjoy music, made telephone banking safer and provided feedback on risky behaviour to drivers.' These are just some of the novel creations and applications being pursued within the group, whose project funding comes from government agencies and via industrial collaborations. The laboratory collaborates broadly, both within Japan and internationally. For instance, the hot topic of driverless vehicles has generated a worldwide network of researchers and manufacturers, who are working to make autonomous transport both safe and acceptable to society. Nagoya University hosts a major biennial workshop on DSP for in-Vehicle and Mobile Systems, which attracts keynote speakers from around the world, including the US, India and Europe. The eighth of these conferences was held in October 2018. Takeda says: 'At the first of these workshops in 2003, we could barely envisage the advances we have now made in distant speech recognition, deep learning for object identification and fully autonomous driving. We see the next important stage as greater harmonisation between humans and automated vehicles.' Today, the biggest project group within the Takeda Laboratory is working on driverless vehicles. The problems of automatically navigating a vehicle through various streetscapes and ensuring clear communication channels between the driver-operator and the car draw on all the laboratory's expertise in sensors and signal processing. Takeda says: 'We want to make the vehicle more responsive and less frustrating to the user.' He explains today's artificial intelligence (AI) can map the best route from A to B and get the passengers there safely, but finds it harder to deal with impulsive and perhaps irrational commands we humans process naturally and easily. These could include wanting to take a different route, making a quick stop at a grocery store, driving at a different speed or taking a rest break. When we are driving ourselves or talking to a human driver, it is easy to satisfy these preferences and it is frustrating to a user if these wants cannot be communicated to an automated vehicle.

          Related collections

          Author and article information

          Journal
          Impact
          impact
          Science Impact, Ltd.
          2398-7073
          June 13 2019
          June 13 2019
          : 2019
          : 5
          : 32-35
          Article
          10.21820/23987073.2019.5.32
          © 2019

          This work is licensed under a Creative Commons Attribution 4.0 Unported License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

          Earth & Environmental sciences, Medicine, Computer science, Agriculture, Engineering

          Comments

          Comment on this article