Engineering Commons^™

Robot Learning From Human Observation Using Deep Neural Networks, Michael Elachkar

Electronic Theses and Dissertations

Industrial robots have gained traction in the last twenty years and have become an integral component in any sector empowering automation. Specifically, the automotive industry implements a wide range of industrial robots in a multitude of assembly lines worldwide. These robots perform tasks with the utmost level of repeatability and incomparable speed. It is that speed and consistency that has always made the robotic task an upgrade over the same task completed by a human. The cost savings is a great return on investment causing corporations to automate and deploy robotic solutions wherever feasible.

The cost to commission and set …

Localization And Mapping Of Unknown Locations And Tunnels With Unmanned Ground Vehicles, Doris Turnage

Electronic Theses and Dissertations

The main goals of this research were to enhance a commercial off the shelf (COTS) software platform to support unmanned ground vehicles (UGVs) exploring the complex environment of tunnels, to test the platform within a simulation environment, and to validate the architecture through field testing. Developing this platform will enhance the U. S. Army Engineering Research and Development Center’s (ERDC’s) current capabilities and create a safe and efficient autonomous vehicle to perform the following functions within tunnels: (1) localization (e.g., position tracking) and mapping of its environment, (2) traversing varied terrains, (3) sensing the environment for objects of interest, and …

Towards Improving Human-Robot Interaction For Social Robots, Saad Khan

Electronic Theses and Dissertations

Autonomous robots interacting with humans in a social setting must consider the social-cultural environment when pursuing their objectives. Thus the social robot must perceive and understand the social cultural environment in order to be able to explain and predict the actions of its human interaction partners. This dissertation contributes to the emerging field of human-robot interaction for social robots in the following ways: 1. We used the social calculus technique based on culture sanctioned social metrics (CSSMs) to quantify, analyze and predict the behavior of the robot, human soldiers and the public perception in the Market Patrol peacekeeping scenario. 2. …

Reconode: Towards An Autonomous Multi-Robot Team Agent For Usar, Kang Li

Electronic Theses and Dissertations

Urban search and rescue (USAR) robots can benefit from small size as it facilitates movement in cramped quarters. Yet, small size limits actuator power, sensor payloads, computational capacity and battery life. We are alleviating these issues by developing the hardware and software infrastructure for high performance, heterogeneous, dynamically-reconfigurable miniature USAR robots, as well as a host of other relevant applications. In this thesis, a generic modular embedded system architecture based on the RecoNode multiprocessor is proposed, which consists of a set of hardware and software modules that can be configured to construct various types of robot systems for dynamic and …

A Multi-Objective No-Regret Decision Making Model With Bayesian Learning For Autonomous Unmanned Systems, Matthew Howard

Electronic Theses and Dissertations

The development of a multi-objective decision making and learning model for the use in unmanned systems is the focus of this project. Starting with traditional game theory and psychological learning theories developed in the past, a new model for machine learning is developed. This model incorporates a no-regret decision making model with a Bayesian learning process which has the ability to adapt to errors found in preconceived costs associated with each objective. This learning ability is what sets this model apart from many others. By creating a model based on previously developed human learning models, hundreds of years of experience …

Coverage Path Planning And Control For Autonomous Mobile Robots, Mohanakrishnan Balakrishnan

Electronic Theses and Dissertations

Coverage control has many applications such as security patrolling, land mine detectors, and automatic vacuum cleaners. This Thesis presents an analytical approach for generation of control inputs for a non-holonomic mobile robot in coverage control. Neural Network approach is used for complete coverage of a given area in the presence of stationary and dynamic obstacles. A complete coverage algorithm is used to determine the sequence of points. Once the sequences of points are determined a smooth trajectory characterized by fifth order polynomial having second order continuity is generated. And the slope of the curve at each point is calculated from …