Amy R. Wagoner

Humanoid robots rescuing humans and extinguishing fires for Cooperative Fire Security System using HARMS

Fires cause billions of dollars in damage and thousands of deaths each year. Firefighting robots are being deployed around the world to reduce the loss of human life and the amount of property damage. High-rise buildings are used for both business and family homes. Buildings with dozens of floors present a great challenge to firefighters. Firefighter ladders cannot reach high enough to fight fires at the top of the building. Going into the building itself, in order to extinguish the blazing fire, is typically too dangerous and puts firefighters at risk. Monitoring, locating, and extinguishing the fire in the smallest amount of time is crucial to controlling fires in highrise buildings. This paper introduces humanoid robots capable of moving towards and extinguishing a fire and locating and rescuing any humans unlucky enough to be trapped in the inferno. This paper is one part of a Cooperative Fire Security System using HARMS (CFS2H) that detects, locates, and extinguishes a fire and rescues human beings using the Human, Agent, Robot, Machine, Sensor (HARMS) protocol.

On Identifying Authors with Style

Stylometry is the quantified (often statistical) analysis of author style as a set of (usually morphosyntactic) features expressed in several documents by the author. The focus of this paper is a task to which stylometry is often applied: authorship attribution, the question of identifying or confirming the author of a text based on the known body of work. We analyze a feature set previously introduced in the field, using a tool and corpus already available. Decomposing the set, we identify the features that seem to have contributed the most to accurate performance. In re-composing the set under different objectives - first, for English-only document sets, and then for possible multi-language use - we identify smaller sets of feature combinations that work well together in accurate performance. We then outline our continuing work based on the results we obtain.

Style Features for Authors in Two Languages

Stylometry is the measurement of certain expressible features of writing style, and its uses include the characterization of authors for recognition in cases of text whose authorship is disputed or unknown. This work builds upon previous investigation into the success of a particular feature set on a particular corpus. We explore the creation and testing of a small corpus spanning multiple languages and character sets, and the building of a feature set for use in author attribution problems over that corpus. In-depth analysis of results is used to motivate further work.

A Robust Human-Robot Communication System Using Natural Language for HARMS

Abstract This paper presents a robust human-robot communication system using natural language for HARMS (Human, Agent, Robot, Machine, Sensor). HARMS is a unique model designed for multi-agent systems. The human-robot communication system focuses specifically on allowing humans to easily and naturally communicate with other agents in the multi-agent system. The communication system uses specially designed algorithms that can accept any input, classify the input as one of the three message types in HARMS, and interpret the input to machine readable commands to be transmitted to other agents. The communication system is robust because it does not rely on a specific set of input (i.e. direct commands) or syntax. The user does not need any prior training and can communicate with the system naturally. Tests were performed on the system for each of the three sentence types (imperative, interrogative, and declarative) with an overall accuracy of 96.6%.

Realization of an Autonomous, Air-to-Air Counter Unmanned Aerial System (CUAS)

The proliferation of small Unmanned Aerial Systems (UASs) has led to a security gap in the defense of strategic installations and at public events. One of the most proven and low-regret methods employed by Counter Unmanned Aerial Systems (CUASs) is entanglement of the hostile UAS in a net carried by a hunter UAS. Typically these hunter UASs are controlled by a human pilot. We employ a ground based RADAR system for tracking the target UAS and command the hunter UAS to follow the target UAS, using the Robot Operating System (ROS), the MAVLink protocol, and the PX4 autopilot. This system is fully autonomous, which reduces cost and response time when compared to human-in-the-loop systems. In addition, a novel cylindrical net design is presented. We demonstrate the systems effectiveness through field testing.

Survey on Detection and Tracking of UAVs Using Computer Vision

Small unmanned aerial vehicles (UAVs) have become increasingly popular in the last several years. This paper explores numerous methods to detect and track small UAVs using computer vision.

Towards a vision-based targeting system for counter unmanned aerial systems (CUAS)

Unmanned aerial vehicles (UAVs) are rapidly increasing in popularity. Despite attempts at regulation, stopping small, Class 1 (typically hobby-grade) UAVs from entering protected or sensitive airspace is an unsolved problem. Many companies and researchers offer a piece of a solution, but as of this writing, there is no publicly available, feasible, end-to-end solution. Ultimately, what is needed is a sensor-based system that autonomously detects, tracks, and neutralizes/disables an incoming UAV. However, such a system is currently not available, so as development toward that goal continues, a temporary solution is required. Augmenting the skill, dexterity, and processing power of human pilots with inexpensive cameras and computer vision algorithms can offer such a solution. The foundations of a framework for a system that uses computer vision to target and ultimately destroy a target in mid-air is introduced. The proposed solution utilizes a light-weight, inexpensive UAV with an on-board camera. The detection and tracking is performed in real-time on a companion computer mounted to the frame of the vehicle, with ROS as the primary communication infrastructure. Initial simulations provide insight into the feasibility of using computer vision with a monocular camera to offer reliable assistance to the pilot.

A task manager using an ontological framework for a HARMS-based system

Recently, conversational interaction with technology has made its way into popular commercial use. Advancements in natural language processing have made that possible. Now, imagine a future where the average person can have a team of robots and smart devices working together to accomplish daily tasks and all one has to do is interact with the system naturally. For this theoretical team to exist, an interaction system must be developed that can translate utterances and autonomously organize and direct the agents into completing the task. This paper presents a task manager that uses on ontology to divide tasks into subtasks and finds the most capable agent to complete the task. The task manager is an extension of a robust dialogue manager that users can communication naturally with. Two ontologies were developed as initial steps towards a task manager for a multi-agent system. An experiment was conducted to test the combination of the dialogue manager and the task manager.