July 2022 Vol. 20 No. 7

Front-line Researchers

• Ryuichiro Higashinaka, Visiting Senior Distinguished Researcher, NTT Human Informatics Laboratories/NTT Communication Science Laboratories

  

  Abstract
  Dialogue systems have made great progress over the last few years due to the application of deep learning and the spread of technologies that enable people to interact with voice agents on smartphones, personal robots, and other devices. Ryuichiro Higashinaka, a visiting senior distinguished researcher of NTT Human Informatics Laboratories/NTT Communication Science Laboratories and professor of the Graduate School of Informatics, Nagoya University, is aiming to create a dialogue system that allows humans and computers to understand each other and intelligently collaborate by clarifying the principles of natural-dialogue interaction between them. We interviewed him about the progress of his research and his attitude as a researcher.

Rising Researchers

• Takuhiro Kaneko, Distinguished Researcher, NTT Communication Science Laboratories

  

  Abstract
  When people look at photos, they can estimate three-dimensional (3D) information, such as depth, from their experience and knowledge, but computers have difficulty in doing so because they cannot have such experience and knowledge. We spoke to Takuhiro Kaneko, a distinguished researcher who developed a novel deep learning model that can learn 3D information from standard 2D images such as those on the web.

Feature Articles: Optical and Wireless Transmission Technologies for IOWN/6G

• Research and Development for Pioneering a New Communications Paradigm with Wide-area Coverage

  

  Abstract
  Research and development at NTT Network Innovation Laboratories aims to establish elemental technologies for next-generation communication networks envisioned under NTT’s Innovative Optical and Wireless Network (IOWN) and the 6th-generation mobile communication system (6G). These technologies, which include advanced and high-capacity backbone optical transmission networks and extended coverage of wireless communications, are being developed to support dramatic changes in the information society such as the expansion of remote work due to the COVID-19 pandemic. This article introduces optical/wireless transmission technologies and systemization technologies currently being researched and developed at NTT Network Innovation Laboratories.

• Future Development of Digital Coherent Optical Transmission Technology

  

  Abstract
  Digital coherent optical transmission technology―which digitally incorporates physical quantities such as amplitude, phase, and polarization and maximizes transmission performance through advanced signal processing―is the latest generation of optical transmission technology; however, the technology must be further developed to implement the Innovative Optical and Wireless Network (IOWN). The latest trends and future development of digital coherent optical transmission technology are described in this article from the perspectives of high-speed and high-capacity transmission, low-power devices, and software-based autonomous control.

• Research and Development of Scalable Optical Transport Technologies

  

  Abstract
  This article discusses the current state and prospects of scalable optical transport technologies that can dramatically expand the optical amplification and electrical signal processing bandwidths for achieving a Pbit/s-class long-range optical network toward IOWN (the Innovative Optical and Wireless Network) All-Photonics Network. We explain the optical parametric amplification repeater technology, which has the potential to achieve longer transmission distances while expanding the amplification bandwidth of conventional optical amplification repeaters by more than 2.5 times. We also look into the space division multiplexing optical communication technology that uses multiple-input and multiple-output signal processing and has the potential to increase transmission capacity by more than 10 times at the same cladding diameter as conventional optical fibers.

• R&D Activities of Core Wireless Technologies toward 6G Radio Access

  

  Abstract
  Technical research for the 6th-generation mobile communication system (6G) expected to be implemented in the 2030s has been advanced to achieve extreme high data rate/capacity, extreme low latency, extreme high reliability, and extreme coverage extension for non-terrestrial areas. In this article, we introduce the following core wireless technologies developed by NTT Network Innovation Laboratories toward 6G, i.e., orbital angular momentum multiple-input multiple-output (OAM-MIMO) multiplexing transmission, underwater acoustic communication, and wireless-link-quality prediction.

Feature Articles: ICT Platform for Connected Vehicles Created by NTT and Toyota

• Overview of Technical Development and Verification in the Connected-vehicle Field

  

  Abstract
  As technological innovations, such as connectivity, automation, sharing, and electrification, bring major changes to the automotive industry, expectations for and the importance of information and communication technology (ICT) are increasing rapidly in the industry. The NTT Group and Toyota Motor Corporation are collaborating on the research and development of an ICT platform for connected vehicles. They conducted joint field trials from 2018 to 2020 and established the basic technology through various use cases and verification of the platform. In the Feature Articles in this issue, the NTT Group operating companies and NTT laboratories that are participating in the collaboration present the details of the field trials, the results, technologies applied, value provided, and future issues.

• Activities and Results of Field Trials—Reference Architecture for a Connected-vehicle Platform

  

  Abstract
  The NTT Group and Toyota Motor Corporation are collaborating on research and development of an information and communication technology platform for connected vehicles. They conducted joint field trials and verified the platform across a variety of use cases from 2018 to 2020. They also established basic technologies in the course of these trials. This article presents an overview of the reference architecture for the connected-vehicle platform, which collects, stores, and uses controller area network data (vehicle control data) and image data sent from in-vehicle devices. It also reports on the technical results obtained and challenges identified during the implementation of the platform and the field trials.

• Activities and Results of Field Trials—Network Edge Computing Platform

  

  Abstract
  Toyota Motor Corporation and the NTT Group conducted field trials to verify an information and communication technology platform for connected vehicles over a three-year period beginning in 2018 and shared their respective technologies and expertise regarding connected vehicles. Distributed processing using edge nodes increased the efficiency and processing speed of the platform. However, the distribution of processing sites created new challenges. To address these challenges, we developed an architecture in which multiple network functions are allocated to edge nodes and verified its effectiveness through these field trials.

• Real-time Spatiotemporal Data-management Technology (Axispot™)

  

  Abstract
  To enable the obstacle-detection use case, in which vehicles approaching an obstacle (e.g., falling object) on the road are immediately notified of the obstacle, and the lane-specific congestion detection use case, in which the number of vehicles in each lane on the road is determined, it is necessary to store data sent simultaneously from a large number of connected vehicles, search the data in real time for vehicles present within a certain area (mesh area, road, parking lot, etc.) at any specific time, and determine the number of these vehicles. This article describes the real-time spatiotemporal data-management technology (Axispot™) that we are developing to meet these requirements.

• Selective Vehicle-data-collection Algorithm

  

  Abstract
  In an obstacle-detection use case, in which a monitoring system keeps track of an obstacle on the road, the system needs to continuously collect the latest images of the obstacle captured using onboard cameras. Although image-recognition technology can be used to accurately select relevant images (images that capture the obstacle in question), computational resources available in a vehicle are too limited to execute this task. In addition, transferring all images via a mobile network to the cloud incurs considerable communication costs. To solve these problems, we devised a technology that estimates the range of the area that can be captured with each camera (hereafter, visible range) and selectively collects only the relevant images. The visible range is estimated on the basis of meta-information, such as vehicle position, direction of movement, and camera angle of view.

• Vertically Distributed Computing Technology

  

  Abstract
  We developed a technology that quickly shares information found by a connected vehicle with other vehicles. For example, when a connected vehicle finds an obstacle on the road, the technology can transmit information about it quickly to other vehicles. This quick notification is achieved by offloading part of the processing of the collected obstacle information to network-edge nodes and transmitting interim results to vehicles near the obstacle. However, in urban areas, the delay in notification may become large because a large number of vehicles connect to a small number of network-edge nodes; thus, the volume of data received from these vehicles may overwhelm the computing resources of these nodes. To solve this problem, we also developed a technology that dynamically selects which computer will execute any particular notification processing on the basis of the states of the connected vehicles. Using this technology, obstacle information can be transmitted quickly even when a large number of vehicles are connected to a small number of network-edge nodes.

• Lane-specific Traffic-jam-detection Technology

  

  Abstract
  Dynamic maps are being constructed to support automated driving and advanced navigation. They combine high-precision map information with traffic-related information, such as that about traffic controls and jams. We at NTT believe that detecting lane-specific traffic jams, such as those caused by a queue of vehicles waiting to enter the parking lot of a commercial facility or by vehicles parked on the street, and providing information on these jams will enable unprecedentedly advanced navigation. This article describes a technology for detecting lane-specific traffic jams on the basis of information that can be collected from connected vehicles.

• Technology for Calculating Suddenness Index for Aggregated Values

  

  Abstract
  We developed a technology for calculating the suddenness index for aggregated values to reduce the amount of computation and communication for video processing needed to detect lane-specific traffic jams. This technology aggregates the number of connected vehicles for each mesh on a map and quantifies the degree of deviation from the ordinary state. This article gives an overview of this technology and describes the value it provides and future issues based on the verification conducted for this lane-specific traffic-jam use case in field trials.

Regular Articles

• Unsupervised Depth and Bokeh Learning from Natural Images Using Aperture Rendering Generative Adversarial Networks

  

  Abstract
  Humans can estimate the depth and bokeh effects from a two-dimensional (2D) image on the basis of their experience and knowledge. However, computers have difficulty in doing this because they logically cannot have such experience and expertise. To overcome this limitation, a novel deep generative model called aperture rendering generative adversarial network (AR-GAN) is discussed. AR-GAN makes it possible to control the bokeh effects on the basis of the predicted depth by incorporating an optical constraint of a camera aperture into a GAN. During training, AR-GAN requires only standard 2D images (such as those on the web) and does not require 3D data such as depth and bokeh information. Therefore, it can alleviate the application boundaries that come from the difficulty in collecting 3D data. This technology is expected to enable the exploration of new possibilities in studies on 3D understanding.

Global Standardization Activities

• Report of the 9th ITU-T TSAG (Telecommunication Standardization Advisory Group) Meeting

  

  Abstract
  The 9th meeting of the Telecommunication Standardization Advisory Group (TSAG) of the International Telecommunication Union - Telecommunication Standardization Sector (ITU-T), the final meeting of the study period (2017−2021) for the World Telecommunication Standardization Assembly (WTSA-20), was held in an online conference from January 10 to 17, 2022. The 4th Inter-regional Meeting, a preparatory meeting for WTSA-20, was also held on January 6 before the TSAG meeting. This article describes the main results of the 9th TSAG meeting.

External Awards

• External Awards