Byung-Cheol Min

A natural language exchange model for enabling human, agent, robot and machine interaction

Models of communications in heterogeneous systems support exchange between agents of different types. A key component is making the heterogeneous agents appear indistinguishable to and from each other in terms of language, to normalize communication. A goal is to act as an open system, where the agents can come and exit as needed by the requirements of the overall goal of the system. The main goal of this research is the creation of a communicative model to support interaction, organization and collective intelligence features between a heterogeneous set of agents as machines, robots, software agents, and humans, all working in a cooperative organization. Communication appears as a natural language interface between all agents to enable clear, indistinguishable communication between all within the organization.

M2M infrastructure to integrate humans, agents and robots into collectives

Organizations are pervasive in all aspects of human society. Most large-scale goals are carried out through the cooperation of a group of humans typically working with technologies such as robots and machines. The main goal of this research is the creation of a model and architecture to support networking, communication, interaction, organization and collective intelligence features between machines, robots, software agents, and humans. The model will allow each of these actors to cooperatively work together to accomplish large-scale goals. While machines, robots, software agents and humans are very different in their capabilities, embodiment and inherent behaviors, a core goal is to make them indistinguishable in terms of acting in an organization. When a robot communicates to another actor, it is not concerned with the physical makeup of that actor, only in its ability to solve a goal or execute a task. The goal of indistinguishable actors is not at the level of a Turing test, it gives the organization the flexibility to act as an open system, where the actors can come and exit as needed by the requirements of the overall goal set.

Development of a Micro Quad-Rotor UAV for Monitoring an Indoor Environment

The purpose of this paper is to develop a micro UAV (Unmanned Aerial Vehicle) as the platform for monitoring an indoor environment, more specifically, a quad-rotor aircraft that has strong advantages of its small size, stable hovering and precise flight. To begin with, we analyze the dynamics of a quad-rotor aircraft, and introduce control strategies based on the PD control. Then, the developed micro quad-rotor UAV, equipped with micro controllers, various sensors, and a wireless camera, is presented and is compared with the DraganFlyer commercial quad-rotor aircraft. Finally, experimental results are also provided so as to illustrate stable flight performances.

Fuzzy Logic Path Planner and Motion Controller by Evolutionary Programming for Mobile Robots

A fuzzy logic controller (FLC) for mobile robots is designed in hierarchical structure. The designed FLC consists of two levels: the planner level and the motion control level. The planner level generates a path to the destination by avoiding obstacles. The singleton outputs of the planner are obtained by using lines and arc methods. The lower motion control level calculates the robots wheel velocity so as to follow the path generated by the planner as to the current robot posture. The fuzzy singleton outputs are obtained by heuristics and tuned by evolutionary programming. The applicability of the controller is demonstrated by using robot soccer system.

Using Mobile Robots to Establish Mobile Wireless Mesh Networks and Increase Network Throughput

We discuss the proof of concept that gives mobile robotic units the ability to provide a mobile wireless mesh network providing wireless service to end-clients and also demonstrate the ability to increase the throughput of this mobile wireless mesh system by autonomously reducing the hop count required for network traffic to transit through. In doing so, this proof-of-concept contributes to future development of a robust system which can be deployed and utilized in different situations and industry.

Implementing HARMS-based indistinguishability in ubiquitous robot organizations

As robots become more pervasive and ubiquitous in the lives of humans, they become increasingly involved in every aspect of the lives of humans. People expect that robots will take on tasks to simplify our lives, by working with humans just as other humans do, in normal organizations and societies. This labor specialization, by ubiquitous robots, allows humans more comfort, time or focus to concentrate on higher level desires or tasks. To further this unification of relationships, the defined line between humans and other robots must become somewhat indistinguishable. This ever increasing degree of indistinguishability provides that we care less about who or what executes a task or solves a goal, as long as that entity is capable and available. In this paper, we propose a model and a simple example implementation which minimizes the strict line between humans, software agents, robots, machines and sensors (HARMS) and reduces the distinguishability between these actors.

Self-orientation of directional antennas, assisted by mobile robots, for receiving the best wireless signal strength

In our previous work, we presented autonomous, self-organizing wireless networks using multiple mobile robots, which enabled the desired wireless coverage in the form of a mesh network and a point-to-point network. Capacities to cover the desired area using multiple robots, all carrying omnidirectional antennas, were demonstrated. However, the use of omnidirectional antennas did not prove effective in covering a sufficiently large distance. Hence, in this paper, we introduce the use of directional antennas to increase the range of the wireless network, and later apply this concept to extending a wireless network over complex terrain. As the first step to using directional antennas, we will present a pattern-based search algorithm to address the problem of self-orientation of a Directional Wireless Network (DWN). The algorithm will find the orientation of antennas that enables them to receive the best possible Received Signal Strength Indication (RSSI). Preliminary experimental results will be shown that demonstrate the ability of the algorithm, assisted by mobile robots with pan-tilt devices for the antennas, to automatically find the maximum RSSI available. Finally, we will conclude with a discussion of findings from this paper and applications of the use of directional antennas.

Design of a networked robotic system capable of enhancing wireless communication capabilities

In this paper, we present the design of a networked robotic system capable of enhancing wireless communication capabilities. The core of the system is active antenna tracking with directional antennas. The proposed system is decentralized and consists mainly of a mobile robot system and a command center system. Each system is equipped with off-the-shelf network devices such as antennas, access points (AP), and network switches. For directional antennas to be beneficial to our system, we propose a weighted centroid algorithm (WCA), which is a method for active antenna tracking and direction of arrival (DOA) estimation. Through extensive field experiments in different environments and with different antenna selections, such as omni-to-omni, omni-to-directional, directional-to-directional antennas, we demonstrate the feasibility of our proposed system. We expect that our system can be applied in a variety of rescue, surveillance, and emergency scenarios where high bandwidth and long distance communications are needed.

Using directional antennas as sensors to assist fire-fighting robots in large scale fires

Humans will replace human labor with new robotics technologies, especially where humans can be placed in danger situations or task domains. Evolving sensor and robotic technologies allow the transfer of humans from mundane, dangerous or difficult tasks, leaving robots to apply their specific capabilities to replace humans daily routines or hazardous tasks. Commonly, humans work in teams to resolve difficult scenarios, such as the aftermath of some natural or man-made disaster. Communication between each and every team member is critical to resolve relief efforts or remediation, in most disasters. This research presents robotic technology developed to remediate the long lead time to re-establish or develop network infrastructure in the case of a disaster situation. The specific application and test domain of this research, is with fire fighting.

Heuristic optimization techniques for self-orientation of directional antennas in long-distance point-to-point broadband networks

A self-orientation system for a directional antenna is capable of determining the best orientation to receive the strongest wireless signal. In the event of two antennas being deployed randomly or deployed in a dense space where the effects of multipath and other wireless interference exist, efficient search algorithms are required to find the best orientation. Therefore, this paper presents four heuristic optimization techniques for the self-orientation of directional antennas in such events: Pattern Search method, Downhill Simplex method, DIRECT method, and Genetic Algorithm. The modification of each technique for this orientation problem is described, and the performance of each algorithm using different test cases with real world experiments is also described. From our study, we show that the Pattern Search method is the most suitable optimization technique for the self-orientation of directional antennas in long-distance point-to-point broadband networks.