This study aims to acquire RL models for mobile robots to avoid pedestrians in unknown urban environments using deep reinforcement learning. Training is performed in urban environments in a virtual world created by the Unity game engine. The mobile robot runs using only monocular camera images and positional information, and does not use any external sensors other than the monocular camera, such as a LiDAR. Not only the current step, but also the last 5 steps are utilized for input states in learning. This is so that the robot can learn and predict the pedestrians’ movement. Since this is a challenging learning task for the robots, curriculum learning, in which the difficulty of the learning task increases step by step, is adapted. As a result of the learning, the robot acquired the ability to reach the goal while avoiding pedestrians, even in an unknown urban environment including pedestrians with unknown color appearances.

In order to improve safety, operational economics, and environmental sustainability, the International Civil Aviation Organization (ICAO) has established a collaborative environment that promotes the sharing of comprehensive information, not only between ground-to-ground systems but also between aircrafts and corresponding air traffic management systems. However, the existing Air Traffic Control (ATC) system heavily relies on voice communication, which is difficult to satisfy the demands of Trajectory Based Operations (TBO) by effectively coordinating the 4-Dimensional Trajectory (4DT) across various systems and stakeholders. This paper identifies the concept of connected aircraft, outlines potential implementation challenges, and explores additional functional capabilities that could enhance situational and operational awareness. Moreover, based on the live flight experiment, the validation of coordination method and information exchange between the aircraft and ground systems by using proposed system architecture and IP data link service are presented. Finally, we discuss the challenges and issues that need to be addressed for establishing a collaborative operational environment to realize 4DT negotiation through a system-wide information management environment.

A collaborative environment for system-wide flight and flow information exchange is essential to achieve global seamless air traffic management operation. This collaborative information exchange will provide a shared operational image to all relevant parties in order to achieve seamless operation both in the planning phase and the execution phase. However, the current aviation communication networks and information management systems cannot satisfy the requirement for collaborative information sharing. In this paper, the architecture and the collaborative information exchange technology to support coordination between ground-to-ground and air-to-ground systems are proposed. Moreover, the observations and analysis of validation exercise based on the local evaluation system are reported. Finally, the problems and challenges for constructing the collaborative operating environment through a system-wide information management are analyzed and discussed.

The System Wide Information Management (SWIM) concept has been discussed for the standardization of the data format and exchange protocol internationally in order to share the necessary information efficiently and safely in the area of civil aviation. Therefore, aircraft access to SWIM (AAtS) is a key function to achieve rich information exchange between the aircraft and ground systems. However, it is difficult for current air-to-ground communication systems to satisfy the requirement of SWIM. In this paper, we present validation test for availability of Aeronautical Mobile Airport Communications System (AeroMACS) as a wireless media to achieve the AAtS in the airport. We carried out field taxiing experiments based on the AeroMACS and SWIM prototype systems at the Sendai airport. Furthermore, we conducted validation tests of Quality of Service (QoS) function of AeroMACS for accessing to ground SWIM systems. The results show the effectiveness of AeroMACS for AAtS.

System wide information management (SWIM) is a recent concept for providing efficient and safe information sharing in civil aviation. The goal in implementing SWIM is to achieve seamless air traffic management (ATM) services worldwide through the efficient integration of the current ATM systems. In this paper, we consider the wireless media to access SWIM. In the International Civil Aviation Organization (ICAO), the aeronautical mobile airport communications system (AeroMACS) is standardized for the next generation airport surface communication system. It is effective to share various types of information among air traffic controllers, pilots, and airport operators, not only on airport surface, but also in taking off and landing by AeroMACS. However, AeroMACS is intended to be used at speeds of 120km/h or below. In this paper, we study the possibility of using AeroMACS while an aircraft is moving at over 120km/h, as would occur in takeoff and landing situations. We conducted flight tests using an AeroMACS standard-compliant prototype system and an experimental aircraft. In the experiments, we obtained a received signal strength indicator (RSSI) to investigate 5GHz ground-to-air propagation. The results revealed that an onboard antenna configuration involving vertical placement at the top and bottom of the aircraft body is effective in achieving multiple input multiple output (MIMO) operation. Additional throughputs measurements showed that it was possible for AeroMACS to access SWIM both in takeoff and landing situations at an aircraft speed of 200km/h.

Recently, much attention has been paid to unmanned aircraft systems (UAS), especially for civilian purposes such as disaster prevention and transportation. This paper considers big long-flight-type UASs remotely piloted from ground station by radio communication link, since these types of UASs require higher reliability. The purpose of this paper is to consider a communication system which transmits real-time video of the surroundings of aircraft from unmanned aircraft to the ground pilot. In this paper, the aeronautical mobile airport communications system (AeroMACS) is considered as a command and non-payload communications (CNPC) link between unmanned aircraft and ground pilot. Flight tests using the experimental aircraft and AeroMACS prototype system are conducted to obtain the air-to-ground propagation profile. In addition, the placements of airborne antennas are considered, because the positional relationship between airborne antenna and ground fixed antenna is not constant during the flight. The results of flight tests show the effectiveness of our system, and the received signal strength indicator (RSSI) obtained by flight tests has the same tendency as the free space propagation model. Finally, the results of flight tests show that a vertical placement on top and bottom of aircraft body is effective for the multiple inputs and multiple outputs (MIMO) antenna configuration of UAS.

Aeronautical Mobile Airport Communications System (AeroMACS) is being standardized in order to provide new broadband wireless communications on airport surface. AeroMACS will be used for voice-based Air Traffic Control (ATC) services in the future as it is recommended in standards and recommended practices (SARPs) of the International Civil Aviation Organization (ICAO). Therefore, we evaluated the quality of voice over IP (VoIP) over AeroMACS for ATC. We developed the AeroMACS prototype system in Sendai Airport, a middle-size local airport in Japan. We carried out field experiments by using the prototype system to evaluate the quality of VoIP. In this paper, we provide experimental results and useful information for designing the AeroMACS system for VoIP-based ATC and airline operational control (AOC) services.

Aeronautical Mobile Airport Communications System (Aero MACS) is expected as high-speed communication technologies among moving aircraft, vehicles, air traffic control center and operational management center in airport area. It is possible to use this system as one of the Aircraft Access to System Wide Information Management (AAtS), too. We have developed the prototype system of Aero MACS for future airport surface communication in our programs in 2014. This paper provides our Aero MACS prototype system compliant with Standard and Recommended Practices (SARPs) for Aero MACS developed by International Civil Aviation Organization (ICAO). We also describe some tests and demonstrations using Aero MACS application for validating the Aero MACS SARPs in this paper. As a result, we can join and contribute to the development activities of Aero MACS SARPs.

We are designing authentication framework for a regional network with concerns on fast authentication and disaster robustness. To achieve this goal, we previously proposed a proactive and distributed authentication framework (PDAF). In this paper, to enhance the robustness of PDAF, we add temporary registration and authentication procedures in a disaster scenario and the distributed regional network key server (RNKS) mechanism. Meanwhile, we optimize PDAF messaging through reducing redundancy to improve the performance. The proposed PDAF is a fully distributed design, which is intrinsically more robust than the existing authentication framework. In particular, we implement the PDAF over an existing regional network and measure the performance of PDAF. This shows that network scale and offered traffic load do not influence the PDAF's authentication time, which is usually around 31 ms under our experiment environment, because neighboring networking devices directly authenticate end devices.

Intelligent spaces based on many networked sensors have been studied in recent years. In this study, a mobile intelligent space using a human-following robot is considered. The proposed system provides various informational supports to the users via the human-following robot. For example, Augmented Reality (AR) is as an application of the proposed system. Generally, positions and orientations of a user camera are needed for AR system. In the proposed system, the human-following robot built local maps around the users while following them. Then, camera position estimation using maps is achieved for AR without using markers. This paper calls the proposed system with map building and informational supports to users “Mobile Intelligent Space”. At first, map building while human following is introduced. Especially, some methods to assure reasonable map building speed and stability simultaneously in wide area are described. Experiment results are also shown in this paper.

This paper introduces development of camera sensor nodes for moving object tracking system with multiple cameras for intelligent space. In the current version of our sensor nodes, image processing circuits such as human extraction based on optical flow, labeling and calculation of human position are implemented in FPGA. The camera sensor nodes share each tracking results via network communication using Zigbee for seamless tracking in wide area. In the paper, tracking method between two sensor nodes are considered and some experiments are shown.

The research field on intelligent environments that consist of many distributed sensors and robots has been expanding. Intelligent environments require the functions of extracting and tracking the multiple objects seamlessly to achieve appropriate services to users under the multi-camera environments. Some tracking systems often prepare the color models of the objects in advance. It is difficult to adopt these models to the tracking of the objects that change their color appearance according to the pose. However, model based tracking is efficient for the tracking in the crowded environment. And also, the object color models have to be valid for seamless tracking in the multi-camera environments. We propose the color histogram based object model configuration. This model termed global model is efficient for object tracking and matching. The eigen space of color histograms configured from color appearance in several poses of the object is utilized for the configuration of the global model. Color histogram models needed for tracking of the object that changed their appearance can be rebuilt from the global model. As results of the first experiments, the object correspondence among the different cameras was achieved empirically, and it was described that the proposed object model is effective for the seamless tracking by the distributed cameras

Robots would be able to coexist with humans and support humans effectively in near future. We proposed the intelligent space in order to achieve such human-centered system. The intelligent space is the space where many intelligent devices, such as computers and sensors, are distributed. The intelligent space achieves the human centered services by accelerating the physical and psychological interaction between humans and intelligent devices. As an intelligent device of the intelligent space, a color CCD camera module, which includes processing and networking part, has been chosen. The intelligent space requires functions of identifying and tracking the multiple objects to realize appropriate services to users under the multi-camera environments. In order to achieve seamless tracking and location estimation, many camera modules are distributed. They cause some errors about object identification among different camera modules. This paper describes appearance based object identification for the distributed vision system in intelligent space to achieve consistent labeling of unknown objects. First, we discuss how to obtain the object color information for constructing the color appearance based model. Then, we propose the global color model based on the color information for the object identification.

Intelligent space is a space where many sensors and intelligent devices are distributed. Mobile robots exist in this space as physical agents, which provide human with services. To realize this, human and mobile robots have to approach each other as much as possible. Moreover, it is necessary for them to perform interactions naturally. It is desirable for a mobile robot to carry out human-affinitive movement. In this research, a mobile robot is controlled by the Intelligent Space through its resources. The mobile robot is controlled to follow walking human as stably and precisely as possible.

Intelligent Space is a space where many sensors and intelligent devices are distributed. Mobile robots exist in this space as physical agents, which provide human with services. To realize this, human and mobile robots have to approach each other as much as possible. Moreover, it is necessary for them to perform interactions naturally. It is desirable for a mobile robot to carry out human-affinitive movement. In this research, a mobile robot is controlled by the Intelligent Space through its resources. The mobile robot is controlled to follow a walking human as stably and precisely as possible.