Robotics Commons^™

End To End Satellite Servicing And Space Debris Management, Aman Chandra, Himangshu Kalita, Roberto Furfaro, Jekan Thanga

Space Traffic Management Conference

There is growing demand for satellite swarms and constellations for global positioning, remote sensing and relay communication in higher LEO orbits. This will result in many obsolete, damaged and abandoned satellites that will remain on-orbit beyond 25 years. These abandoned satellites and space debris maybe economically valuable orbital real-estate and resources that can be reused, repaired or upgraded for future use. Space traffic management is critical to repair damaged satellites, divert satellites into warehouse orbits and effectively deorbit satellites and space debris that are beyond repair and salvage. Current methods for on-orbit capture, servicing and repair require a large service ...

Advanced Inflatable De-Orbit Solutions For Derelict Satellites And Orbital Debris, Aman Chandra, Greg Wilburn, Jekan Thanga

Space Traffic Management Conference

The exponential rise in small-satellites and CubeSats in Low Earth Orbit (LEO) poses important challenges for future space traffic management. At altitudes of 600 km and lower, aerodynamic drag accelerates de-orbiting of satellites. However, placement of satellites at higher altitudes required for constellations pose important challenges. The satellites will require on-board propulsion to lower their orbits to 600 km and let aerodynamic drag take-over. In this work we analyze solutions for de-orbiting satellites at altitudes of up to 3000 km. We consider a modular robotic de-orbit device that has stowed volume of a regular CubeSat. The de-orbit device would be ...

American Sign Language Recognition Using Machine Learning And Computer Vision, Kshitij Bantupalli, Ying Xie

Master of Science in Computer Science Theses

Speech impairment is a disability which affects an individual’s ability to communicate using speech and hearing. People who are affected by this use other media of communication such as sign language. Although sign language is ubiquitous in recent times, there remains a challenge for non-sign language speakers to communicate with sign language speakers or signers. With recent advances in deep learning and computer vision there has been promising progress in the fields of motion and gesture recognition using deep learning and computer vision-based techniques. The focus of this work is to create a vision-based application which offers sign language ...

State Feedback Of Complex Systems Using Fuzzy Cognitive Maps, Vassiliki Mpelogianni, Ioannis Arvanitakis, Peter P. Groumpos

International Journal of Business and Technology

Complex systems have become a research area with increasing interest over the last years. The emergence of new technologies, the increase in computational power with reduced resources and cost, the integration of the physical world with computer based systems has created the possibility of significantly improving the quality of life of humans. While a significant degree of automation within these systems exists and has been provided in the past decade with examples of the smart homes and energy efficient buildings, a paradigm shift towards autonomy has been noted. The need for autonomy requires the extraction of a model; while a ...

A Deep Recurrent Q Network Towards Self-Adapting Distributed Microservices Architecture (In Press), Basel Magableh

Articles

One desired aspect of microservices architecture is the ability to self-adapt its own architecture and behaviour in response to changes in the operational environment. To achieve the desired high levels of self-adaptability, this research implements the distributed microservices architectures model, as informed by the MAPE-K model. The proposed architecture employs a multi adaptation agents supported by a centralised controller, that can observe the environment and execute a suitable adaptation action. The adaptation planning is managed by a deep recurrent Q-network (DRQN). It is argued that such integration between DRQN and MDP agents in a MAPE-K model offers distributed microservice architecture ...

News - Screven-Jenkins Regional Library, Sharon Blank

Georgia Library Quarterly

No abstract provided.

Should Robots Prosecute And Defend?, Stephen E. Henderson

Stephen E Henderson

Localization Using Convolutional Neural Networks, Shannon D. Fong

Computer Engineering

With the increased accessibility to powerful GPUs, ability to develop machine learning algorithms has increased significantly. Coupled with open source deep learning frameworks, average users are now able to experiment with convolutional neural networks (CNNs) to solve novel problems. This project sought to train a CNN capable of classifying between various locations within a building. A single continuous video was taken while standing at each desired location so that every class in the neural network was represented by a single video. Each location was given a number to be used for classification and the video was subsequently titled locX. These ...

Audio To Architecture: House Music As A Form Generator, Polina Timchenko

Architecture Undergraduate Honors Theses

Contemporary music undergoes similar process of creation to that of the design process through computation and variation. House music as a representation of contemporary culture has a layered structure that allows specific characteristics to identify it as house music. Song components can vary and mix in different orders that form new dynamic compositions. I am going to explore the idea that every house music component can be translated into geometry with the use of parametric design techniques.

A Scalable, Chunk-Based Slicer For Cooperative 3d Printing, Jace J. Mcpherson

Computer Science and Computer Engineering Undergraduate Honors Theses

Cooperative 3D printing is an emerging technology that aims to increase the 3D printing speed and to overcome the size limit of the printable object by having multiple mobile 3D printers (printhead-carrying mobile robots) work together on a single print job on a factory floor. It differs from traditional layer-by-layer 3D printing due to requiring multiple mobile printers to work simultaneously without interfering with each other. Therefore, a new approach for slicing a digital model and generating commands for the mobile printers is needed, which has not been discussed in literature before. We propose a chunk-by-chunk based slicer that divides ...

“New” Subjects In Mechatronics Management Education, Peter Kopacek

International Journal of Business and Technology

Process – and manufacturing automation as well as robotics are currently one of the fast growing fields in automation. Advanced process control, cyber-physical systems, industry 4.0 and “advanced robots” are no longer a headline. They are in realization. As a consequence of these developments new social, ethical and human questions appear.

Therefore this contribution is a first report about the continuous “modernization” of the Mechatronics Management BSc and MSc programs which are successful running at UBT. Both programs were developed in the framework of two TEMPUS projects from an international consortium from 2006 to 2009. Since that time new “buzzwords ...

Optimal Control Of Dc Motors Using Pso Algorithm For Tuning Pid Controller, Arnisa Myrtellari, Petrika Marango, Margarita Gjonaj

International Journal of Business and Technology

The DC motors are widely used in the mechanisms that require control of speed. Different speed can be obtained by changing the field voltage and the armature voltage. The classic PID controllers are widely used in industrial process for speed control. But they aren’t suitable for high performance cases, because of the low robustness of PID controller. So many researchers have been studying various new control techniques in order to improve the system performance and tuning PID controllers. This paper presents particle swarm optimization (PSO) method for determining the optimal PID controller parameters to find the optimal parameters of ...

12 - Data Analytics Using Accelerometer Data Obtained From Adxl345 Mounted On A Wi-Fi-Based Remotely Controlled Model Car, Adriana Amyette, Sairam Tangirala, Tae Song Lee

Georgia Undergraduate Research Conference (GURC)

Poster presentation of

“Data Analytics Using Accelerometer Data Obtained From ADXL345 Mounted on a Wi-Fi-Based Remotely Controlled Model Car”

with demonstration of a working remotely-controlled smart car prototype system.

Esense 2.0: Modeling Biomimetic Predation With Multi-Agent Multi-Team Distributed Artificial Intelligence, D. Michael Franklin, Derek Martin

Georgia Undergraduate Research Conference (GURC)

Biologic predation is a complex interaction amongst sets of predators and prey operating within the same environment. There are many disparate factors for each member of each set to consider as they interact. Additionally, they each must seek food while avoiding other predators, meaning that they must prioritize their actions based on policies. eSense provides a powerful yet simplistic reinforcement learning algorithm that employs model-based behavior across multiple learning layers. These independent layers split the learning objectives across multiple layers, avoiding the learning-confusion common in many multi-agent systems. The new eSense 2.0 increases the number of layers and the ...

Generalized Scattering-Based Stabilization Of Nonlinear Interconnected Systems, Anastasiia Usova

Electronic Thesis and Dissertation Repository

The research presented in this thesis is aimed at development of new methods and techniques for stability analysis and stabilization of interconnections of nonlinear systems, in particular, in the presence of communication delays. Based on the conic systems' formalism, we extend the notion of conicity for the non-planar case where the dimension of the cone's central subspace may be greater than one. One of the advantages of the notion of non-planar conicity is that any dissipative system with a quadratic supply rate can be represented as a non-planar conic system; specifically, its central subspace and radius can be calculated ...

Reinforcement Learning In Robotic Task Domains With Deictic Descriptor Representation, Harry Paul Moore

LSU Doctoral Dissertations

In the field of reinforcement learning, robot task learning in a specific environment with a Markov decision process backdrop has seen much success. But, extending these results to learning a task for an environment domain has not been as fruitful, even for advanced methodologies such as relational reinforcement learning. In our research into robot learning in environment domains, we utilize a form of deictic representation for the robot’s description of the task environment. However, the non-Markovian nature of the deictic representation leads to perceptual aliasing and conflicting actions, invalidating standard reinforcement learning algorithms. To circumvent this difficulty, several past ...

Project Janus, Theodore J. Lilyeblade, Jacqueline Worley, Garrison Bybee

Undergraduate Research Symposium - Prescott

The development goal of Project Janus is to design, fabricate, and program two robotic heads that can serve as animatronic chatbots. Each robotic head will be equipped with two USB webcams, a mono speaker within the robot’s mouth, and a pair of microphones. Additionally, each robotic head will feature a three degree of freedom neck, a one degree-of-freedom jaw, and a two degree-of-freedom gimbal for the eyes upon which the cameras will be mounted. The robotic heads will be interfaced to separate internet connected personal computers. Through these computers, they will make use of online speech recognition tools, online ...

A Dexterous, Glove-Based Teleoperable Low-Power Soft Robotic Arm For Delicate Deep-Sea Biological Exploration, Brennan T. Phillips, Kaitlyn P. Becker, Shunichi Kurumaya, Kevin C. Galloway, Griffin Whittredge, Daniel M. Vogt, Clark B. Teeple, Michelle H. Rosen, Vincent A. Pieribone, David F. Gruber, Robert J. Wood

Publications and Research

Modern marine biologists seeking to study or interact with deep-sea organisms are confronted with few options beyond industrial robotic arms, claws, and suction samplers. This limits biological interactions to a subset of “rugged” and mostly immotile fauna. As the deep sea is one of the most biologically diverse and least studied ecosystems on the planet, there is much room for innovation in facilitating delicate interactions with a multitude of organisms. The biodiversity and physiology of shallow marine systems, such as coral reefs, are common study targets due to the easier nature of access; SCUBA diving allows for in situ delicate ...

Exploring The Effect Of Different Numbers Of Convolutional Filters And Training Loops On The Performance Of Alphazero, Jared Prince

Masters Theses & Specialist Projects

In this work, the algorithm used by AlphaZero is adapted for dots and boxes, a two-player game. This algorithm is explored using different numbers of convolutional filters and training loops, in order to better understand the effect these parameters have on the learning of the player. Different board sizes are also tested to compare these parameters in relation to game complexity. AlphaZero originated as a Go player using an algorithm which combines Monte Carlo tree search and convolutional neural networks. This novel approach, integrating a reinforcement learning method previously applied to Go (MCTS) with a supervised learning method (neural networks ...

Deep Rc: Enabling Remote Control Through Deep Learning, Jaron Ellingson, Gary Ellingson, Tim Mclain

All Student Publications

Human remote-control (RC) pilots have the ability to perceive the position and orientation of an aircraft using only third-person-perspective visual sensing. While novice pilots often struggle when learning to control RC aircraft, they can sense the orientation of the aircraft with relative ease. In this paper, we hypothesize and demonstrate that deep learning methods can be used to mimic the human ability to perceive the orientation of an aircraft from monocular imagery.

This work uses a neural network to directly sense the aircraft attitude. The network is combined with more conventional image processing methods for visual tracking of the aircraft ...