Robotics Commons^™

Obstacle Avoidance Subsystem For An Autonomous Robot, Kirstie King

Honors Program Projects

This research project details the design and implementation of the Obstacle Avoidance Subsystem for the Tigertron autonomous robot. This subsystem is designed to function as a smaller part of the whole Software Architecture and has the purpose of detecting, through use of a Laser Rangefinder, obstacles in the vehicle’s environment. Once the hardware is set up and configured, the Tigertron’s central software control architecture requests data from the Laser Rangefinder through a serial communication channel. This data is converted into objects that represent obstacles in the form of polar coordinates. These objects are stored in a container so the central …

Development Of High Resolution Sea Floor Mapping Tools And Techniques, Gabrielle Inglis, J. Ian Vaughn, Clara Smart, Christopher N. Roman

Graduate School of Oceanography Faculty Publications

There is a persistent need for high resolution photographic and bathymetric maps of the sea floor for many research areas in marine geology, biology and archaeology. This poster will present recent work using high frequency multibeam sonars, stereo vision and structured light laser imaging techniques to create maps with centimeter resolution for these applications. This research involves the development of new image and sonar processing techniques that combat the typical difficulties of imperfect navigation information, limited sensor ranges and adverse environmental conditions associated with using marine robotic vehicles in the ocean. Data for this work has been collected with the …

Development Of High Resolution Sea Floor Mapping Tools And Techniques, Gabrielle Inglis, Ian Vaughn, Clara Smart, Chris Roman

Christopher N. Roman

There is a persistent need for high resolution photographic and bathymetric maps of the sea floor for many research areas in marine geology, biology and archaeology. This poster will present recent work using high frequency multibeam sonars, stereo vision and structured light laser imaging techniques to create maps with centimeter resolution for these applications. This research involves the development of new image and sonar processing techniques that combat the typical difficulties of imperfect navigation information, limited sensor ranges and adverse environmental conditions associated with using marine robotic vehicles in the ocean. Data for this work has been collected with the …

Integrating Robotics Into First-Year Experience Courses, Tyson S. Hall, P. Willard Munger

Faculty Works

Robotics are a popular component of many introductory engineering and computer science courses. At Southern Adventist University, the School of Computing faculty decided to integrate robotics into a discipline-specific section of the University’s first-year experience course. The integration of robotics into a first-year experience course has created a hands-on introduction to college life within the Computing discipline while introducing students to the problem-solving process. This paper will introduce a very low-cost robotic platform kit ($50-75) that has been developed for the first-year experience course. Student assessment data from the first offering of this course with the SouthernBot 2.0 kit shows …

A Relaxed Fusion Of Information From Real And Synthetic Images To Predict Complex Behavior, Damian M. Lyons, D. Paul Benjamin

Faculty Publications

An important component of cognitive robotics is the ability to mentally simulate physical processes and to compare the expected results with the information reported by a robot's sensors. In previous work, we have proposed an approach that integrates a 3D game-engine simulation into the robot control architecture. A key part of that architecture is the Match-Mediated Difference (MMD) operation, an approach to fusing sensory data and synthetic predictions at the image level. The MMD operation insists that simulated and predicted scenes are similar in terms of the appearance of the objects in the scene. This is an overly restrictive constraint …

Imirok: Real-Time Imitative Robotic Arm Control For Home Robot Applications, Heng-Tze Cheng, Zheng Sun, Pei Zhang

Zheng Sun

Training home robots to behave like human can help people with their daily chores and repetitive tasks. In this paper, we present Imirok, a system to remotely control robotic arms by user motion using low-cost, off-the-shelf mobile devices and webcam. The motion tracking algorithm detects user motion in real-time, without classifier training or predefined action set. Experimental results show that the system achieves 90% precision and recall rate on motion detection with blank background, and is robust under the change of cluttered background and user-to-camera distance.

Leveraging Mobile Context For Effective Collaboration And Task Management In Disaster Response, Faisal Luqman, Martin L. Griss

Martin L Griss

Collaboration and task management is challenging in distributed, dynamically-formed teams, typical in large scale disaster response scenarios. Ineffective collaboration may result in poor performance and possible loss of life. In this paper, we present Overseer, an agent-based system that exploits context information from mobile devices to facilitate collaboration and task allocation. We describe our system architecture and show how mobile context can be used to create dynamic role-based assignments to support collaboration and effective task management.

Kernelized Locality-Sensitive Hashing For Fast Image Landmark Association, Mark A. Weems

Theses and Dissertations

As the concept of war has evolved, navigation in urban environments where GPS may be degraded is increasingly becoming more important. Two existing solutions are vision-aided navigation and vision-based Simultaneous Localization and Mapping (SLAM). The problem, however, is that vision-based navigation techniques can require excessive amounts of memory and increased computational complexity resulting in a decrease in speed. This research focuses on techniques to improve such issues by speeding up and optimizing the data association process in vision-based SLAM. Specifically, this work studies the current methods that algorithms use to associate a current robot pose to that of one previously …

Exploring Trade-Offs In Auv Controller Design For Shark Tracking, Louis James Bertsch Iv

Master's Theses

This thesis explores the use of an Autonomous Underwater Vehicle (AUV) to track and pursue a tagged shark through the water. A controller was designed to take bearing and range to the shark tag and then control the AUV to pursue it.

First, the ability of a particle filter to provide an accurate estimation of the location of the shark relative to the AUV is explored. Second, the ability of the AUV to follow the shark's path through the water is shown. This ability allows for localized environmental sampling of the shark's preferred path. Third, various path weightings are used …

Anubis: An Attestation Protocol For Distributed Context-Aware Applications, Senaka Buthpitiya, Feng-Tso Sun, Heng-Tze Chen, Patrick Tague, Martin L. Griss, Anind K. Dey

Martin L Griss

Sharing sensitive context information among multiple distributed components in mobile environments introduces major security concerns. The distributed sensing, processing and actuating components of these applications can be compromised and modified or impersonated to extract private and confidential information or to inject false information. In this paper we present the Anubis protocol for remote code attestation and access control of distributed components using remote execution of trusted code. Our Anubis protocol leverages previous work in the fields of wireless sensor networks and secure web browsing. Anubis allows new components to be introduced to the environment without updating existing components. Our implementation …

Mobile Context-Aware Personal Messaging Assistant, Senaka Buthpitiya, Deepthi Madamanchi, Sumalatha Kommaraju, Martin L. Griss

Martin L Griss

A previous study shows that busy professionals receive in excess of 50 emails per day of which approximately 23% require immediate attention, 13% require attention later and 64% are unimportant and typically ignored. The flood of emails impact mobile users even more heavily. Flooded inboxes cause busy professionals to spend considerable amounts of time searching for important messages, and there has been much research into automating the process using email content for classification; but we find email priority depends also on user context. In this paper we describe the Personal Messaging Assistant (PMA), an advanced rule-based email management system which …

Sensorchestra: Collaborative Sensing For Symbolic Location Recognition, Heng-Tze Cheng, Feng-Tso Sun, Senaka Buthpitiya, Martin L. Griss

Martin L Griss

"Symbolic location of a user, like a store name in a mall, is essential for context-based mobile advertising. Existing fingerprint- based localization using only a single phone is susceptible to noise, and has a major limitation in that the phone has to be held in the hand at all times. In this paper, we present SensOrchestra, a col- laborative sensing framework for symbolic location recognition that groups nearby phones to recognize ambient sounds and images of a location collaboratively. We investigated audio and image features, and designed a classifier fusion model to integrate estimates from diff erent phones. We also …

Activity-Aware Mental Stress Detection Using Physiological Sensors, Feng-Tso Sun, Cynthia Kuo, Heng-Tze Cheng, Senaka Buthpitiya, Patricia Collins, Martin Griss

Martin L Griss

"Continuous stress monitoring may help users better understand their stress patterns and provide physicians with more reliable data for interventions. Previously, studies on mental stress detection were limited to a laboratory environment where participants generally rested in a sedentary position. However, it is impractical to exclude the effects of physical activity while developing a pervasive stress monitoring application for everyday use. The physiological responses caused by mental stress can be masked by variations due to physical activity. We present an activity-aware mental stress detection scheme. Electrocardiogram (ECG), galvanic skin response (GSR), and accelerometer data were gathered from 20 participants across …

Omnisense: A Collaborative Sensing Framework For User Context Recognition Using Mobile Phones, Heng-Tze Cheng, Senaka Buthpitiya, Feng-Tso Sun, Martin L. Griss

Martin L Griss

Context information, including a user’s locations and activities, is indispensable for context-aware applications such as targeted advertising and disaster response. Inferring user context from sensor data is intrinsically challenging due to the semantic gap between low-level signals and high-level human activities. When implemented on mobile phones, more challenges on resource limitations are present. While most existing work focuses on context recognition using a single mobile phone, collaboration among multiple phones has received little attention, and the recognition accuracy is susceptible to phone position and ambient changes. Simply putting a phone in one’s pocket can render the microphone muffled and the …

Robust Region Tracking In Multi-Agent Systems Utilizing Sliding Mode Control: Theory And Applications, Mark Bacon

Master's Theses

This thesis presents a methodology to bring controlled agents within a moving region despite agent interaction dynamics, uncertain forces and parameter variation. The logic is derived from traditional Sliding Mode Control theory with an expanded boundary layer which allows position deviation from the region center to specified bounds. As an example of the utility of this control, multiple methods of herding (controlling passive agents by appropriate positioning of controlled agents) are presented.

Room-Level Wi-Fi Location Tracking, Joshua Correa, Ed Katz, Patricia Collins, Martin Griss

Martin L Griss

Context-aware applications for indoor intelligent environments require an appropriately accurate and stable interior positioning system to adapt services to the location of a mobile user or mobile device in a building. Different technologies provide a varying mix of resolution, accuracy, stability and challenges. In this paper we report on our experience using an existing Wi-Fi infrastructure without specialized hardware added to support location tracking. There are several approaches to track the location of Wi-Fi enabled devices within a building such as signal propagation models and signature matching. We found signature matching most effective in our environment. Signature matching is accomplished …

Optimal Port Placement And Automated Robotic Positioning For Instrumented Laparoscopic Biosensors, Brady King

Wayne State University Dissertations

OPTIMAL SURGICAL PORT PLACEMENT AND AUTOMATED ROBOTIC POSITIONING FOR RAMAN AND OTHER BIOSENSORS

by

BRADY KING

January 2011

Advisors: Dr. Abhilash Pandya, Dr. Darin Ellis, Dr. Le Yi Wang, and Dr. Greg Auner

Major: Computer Engineering

Degree: Doctor of Philosophy

Medical biosensors can provide new information during minimally invasive and robotic surgical procedures. However, these biosensors have significant physical limitations that make it difficult to find optimal port locations and place them in vivo. This dissertation explores the application of robotics and virtual/augmented reality to biosensors to enable their optimal use in vivo.

In the first study, human …

Development And Human Performance Evaluation Of A Ground Vehicle Robotic Force-Feedback Tele-Operation System, Ankur Saraf

Wayne State University Theses

ABSTRACT

DEVELOPMENT AND HUMAN PERFORMANCE EVALUATION OF A GROUND VEHICLE ROBOTIC FORCE-FEEDBACK TELE-OPERATION SYSTEM

by

ANKUR SARAF

May 2011

Advisor: Dr. Abhilash K. Pandya.

Major: Electrical Engineering.

Degree: Master of Science.

Modern tele-operation systems are trying to take into account haptic and audio information in addition to visual data to provide as feedback to the tele-operator.This research emphasizes on the development of hardware and software architecture to enhance the tele-operation capabilities of omni-directional inspection robot (ODIS). The system enhances the tele-operation capabilities by introducing force-feedback to the tele-operators. The conventional joystick is replaced with Novint Falcon haptic joystick which gets …

Control Of A Single Ground Vehicle Using Aerial And Onboard Camera Views, Vishal Lowalekar

Wayne State University Theses

Controlling a ground vehicle using only onboard and aerial camera views, can be a tedious task, as it is challenging for the operator to estimate information about the robots location and orientation using only these view. However the visual data can be sufficient for computerized calculation of this information even in the absence of other sensors. This approach is of interest to the military because the use of passive sensors instead of active sensors (e.g. LIDAR) would be easier and more reliable and would not give off detectable signatures.

The goal of this research was to control a ground vehicle …

Adaptive Discrete-Time Controller Design With Neural Network For Hypersonic Flight Vehicle Via Back-Stepping, Bin Xu

Bin Xu

In this article, the adaptive neural controller in discrete time is investigated for the longitudinal dynamics of a generic hypersonic flight vehicle. The dynamics are decomposed into the altitude subsystem and the velocity subsystem. The altitude subsystem is transformed into the strict-feedback form from which the discrete-time model is derived by the first-order Taylor expansion. The virtual control is designed with nominal feedback and neural network (NN) approximation via back-stepping. Meanwhile, one adaptive NN controller is designed for the velocity subsystem. To avoid the circular construction problem in the practical control, the design of coefficients adopts the upper bound instead …