Digital Commons Network^™

Multi Robot Systems: The Eagleknights/Robobulls Small- Size League Robocup Architecture, Alfredo Weitzenfeld

36th Florida Conference on Recent Advances in Robotics

In this paper we present the system architecture of the Eagle Knights/RoboBulls Small Size League RoboCup Team. In this league two teams composed of five autonomous robots each compete against each other in a medium size field. This league is one of the fastest and most thrilling in RoboCup permitting teams to develop complex coordination strategies. We explain the three main components of the architecture: Vision System, AI System and Robots.

Linkage-Based Prosthetic Fingertips: Stability Analysis, Issa A. Ramirez, Craig P. Lusk, Murray E. Maitland

36th Florida Conference on Recent Advances in Robotics

The purpose of this study is to analyze linkage- based prosthetic fingertips. The novel design consists of small four-bar mechanisms attached to each section of the opposing fingers replacing what would be the pulp of normal anatomical fingers. The four-bar mechanisms allow the prosthetic hand to conform to the shape of objects during grasp The goal of these prosthetic fingertips is to maximize the functionality of the hand while minimizing the number of inputs that the user has to control. This is crucial in prosthetics where the user may have limited input options, but it may also be useful in …

A Metric For Planar Displacements, Venkatesh Venkataramanujam, Pierre Larochelle

36th Florida Conference on Recent Advances in Robotics

Metrics, which facilitate the measurement of parameters such as “distance” and “length” are used frequently in rigid body guidance problems. Commonly used metrics have a characteristic of being dependent on the choice of fixed or moving reference frame and the units used. Most motion synthesis algorithms require some notion of the “distance” between two desired locations. The metrics in Euclidean space depend on the coordinate frame and units used. A metric independent of these choices is desirable. In this paper we present a metric which is independent of the choice of fixed coordinate frame.

Position Tracking Performance Of A Redundant Teleoperation System, Mehmet Ismet Can Dede, Sabri Tosunoglu

36th Florida Conference on Recent Advances in Robotics

Teleoperation has captured the interest of robotics researchers for more than two decades. Many focused on the stability problem when the system experiences time delays. Most of the time, guaranteeing stability has overshadowed the tracking performance. This work differentiates teleoperation systems into two groups as limited and unlimited-workspace teleoperation depending on their position tracking priorities. Specifically, this paper examines limited-workspace teleoperation on a redundant system. The slave is modeled to be the virtual representation of a Fanuc LR Mate 100iB, a five degree-of-freedom (DOF) serial industrial manipulator. The master is selected as a two-DOF force-reflecting joystick. Hence, the teleoperation system …

Machine Vision System For Autonomous Asphalt Layer, Anthony Michel, Brandon Chacon, Matthew Laurent, David Perez, Berry Lamy, Ibrahim Tansel

36th Florida Conference on Recent Advances in Robotics

Asphalt laying is a labor-intensive process and creates extensive air pollution. Next generation environment friendly machines need to minimize the emissions and necessary manual labor. Autonomously operating machines are expected to replace the current ones. These machines will need to measure the road profile to perform their operation. Laser based road profile measurement sensors are expensive and require a clean environment to perform their single point or line inspection with a fraction of micron accuracy.

Recently, stereoscopic imaging has been selected by the automobile manufacturers for autonomous driving. In this study performance of the stereoscopic imaging technique of Intel RealSense …

Trilateration-Based Robot Localization With Learned Visual Landmarks, Valeria Salas, Alfredo Weitzenfeld

36th Florida Conference on Recent Advances in Robotics

Many strategies for robot localization exist, such as trilateration and triangulation algorithms, that compute relative distance and orientation of robot to multiple landmarks. These algorithms require predefined knowledge of landmarks. In this paper we describe a trilateration algorithm for robot localization where new landmarks may be defined using deep learning algorithms. We use a single camera to learn new custom objects. This information is passed as input to the system together with the distance to the objects calculated by a previously calibrated distance detection algorithm. A deep learning algorithm is applied to the object detection model making use of TensorFlow’s …

Bldc Actuators Revisited: A New Cost-Effective Design And Manufacturing For Robotic Applications, Sean Bridges, Garhett Smith, Rene Preston, Hakki Erhan Sevil, Michael Reynolds

36th Florida Conference on Recent Advances in Robotics

Brushless Direct Current (BLDC) actuators are recognized for their combined torque capabilities, precision control, and operational versatility, especially in regards to their smaller size. Actuators of this caliber are commonly implemented in high-performance industrial robotic arms, development in exoskeletal technologies, and quadrupedal robotic platforms. Professionally-developed brushless actuators available in the commercial sector deliver in their performance, however at a significant monetary expense. Our aim is to produce cost-efficient robotic actuators which are capable of replicating the design specifications and performance of commercial models. Our research focuses on the understanding and validation of fundamental principles of how brushless motors operate, and …

Using Small Uas For Stem Education: Introducing Robotics And Mechatronics With Drones, Christian Janke, Stefan Kleinke, Kimberly Luthi, Yuetong Lin

36th Florida Conference on Recent Advances in Robotics

Several global developments point to importance of STEM-related education and studies. Every industry sector faces challenges in the recruiting of qualified personnel, due to retiring employees and general economic growth. Also, several domains, foremost automotive and aviation are undergoing a tremendous shift towards electrification to achieve sustainability. Hence, sparking the interest in STEM studies, education and vocational training cannot start early enough. This paper introduces the benefits of the educational use of sUAS by identifying core benefits in the three domains of learning – cognitive, affective, psycho-motor. Preliminary data and survey results from from several science, technology, engineering and math …

Pomdp Library Optimizing Over Exploration And Exploitation In Robotic Localization, Mapping, And Planning, Joyce Anderson Annan, Akram Alghanmi, Marius Silaghi

36th Florida Conference on Recent Advances in Robotics

Localization, mapping, and planning are critical in autonomous robots operating in uncertain environments and in continuous and discrete domains. High-quality probabilistic models for a complex robot depend heavily on details from its environment, involving multiple parameters. However, there is a lack of accurate probabilistic models for existing robots that can handle reasonably the challenges posed by real applications. For most robots, actions are highly non-deterministic. Furthermore, there is a lack of general software packages applicable to new scenarios. Specifically, we propose a POMDP library for optimal planning and localization given new available models, and dedicated to optimize over exploration and …

Preliminary Insights Into Enhancing Human-Robot Teamwork, Kazuhiko Momose, Troy R. Weekes, Thomas C. Eskridge

36th Florida Conference on Recent Advances in Robotics

Advancements in robotics, artificial intelligence, and other automation have highlighted the need for humans to work together with machines in a more flexible and collaborative fashion than previously possible. To formulate effective human-robot teams, it is critical to understand which factors play important roles in enhancing human-robot teamwork. To gain preliminary insights into key factors of effective human-robot teams, we carried out an experiment using an enhanced version of the “Lunar Lander” game, where the goal is to safely land a spacecraft on the moon’s surface in concert with an AI teammate. We specifically attempted to observe some patterns of …

Granular Material Extruder For Autonomous Asphalt Layer, Sebastian Story, Reinel Mota, Osmany D. Gonzalez, Kyle Reynolds, David Perez, Berry Lamy, Ibrahim Tansel

36th Florida Conference on Recent Advances in Robotics

Road paving is a resource-intensive process that is crucial to the world of ground transportation. Autonomous paving solutions are more desirable in comparison to traditional methods when considering the health and well-being of workers, overall project expenses, and quality of the final product. A quarter-scale granular material laying mechanism has been prototyped and integrated into an autonomous platform that facilitates the road paving process. The mechanism designed to compact and extrude granular material performs well with materials that behave similarly to asphalt when in a heated state. Essential prototyping components were limited to additively manufactured plastic and asphalt-like materials to …

Multi-Object Grasping -- Stochastic Grasping From A Pile, Tianze Chen, Adheesh Shenoy, Yu Sun

36th Florida Conference on Recent Advances in Robotics

Grasping multiple objects at once from a pile is common for humans. It makes us efficient in pick and transfer tasks. It is essential for a robot to gain multi-object grasping capability (MOG). This paper defines the multi-object grasping problem and introduces several novel multi-object grasping techniques. These techniques include probability-based pre-grasp potential calculation, a stochastic flexing/extending routine, obtaining end-grasp types, and estimating the number of objects in a grasp. It also proposes a new stochastic grasping strategy for grasping a desired number of objects.

Live Audiovisual Remote Assistance System (Laras) For Person With Visual Impairments, Zachary Frey, Nghia Vo, Varaha Maithreya, Tais Mota, Urvish Trivedi, Redwan Alqasemi, Rajiv Dubey

36th Florida Conference on Recent Advances in Robotics

According to "The World Report on Vision" by World Health Organization (WHO) [1], there are more than 2.2 billion people who have near or distant vision Impairments, out of which 36 million people are classified as entirely blind. This report also emphasizes the importance of social and communal support in enabling individuals with vision impairments to integrate into society and reach their full potential. While performing daily activities and navigating the environment, people with visual impairments (PVIs) often require direct or synchronous assistance [2]. Consequently, there is a growing need for automated solutions to assist in this regard. However, existing …

Renewable Energy Educational Delivery System, Ryan Integlia

36th Florida Conference on Recent Advances in Robotics

Technology advancing rapidly and affecting our daily lives in more ways than ever before, it is clear that technology is now a driving force in our world. STEM disciplines are one of the key driving forces behind human progress, as their efforts have provided us with new levels of comfort and security. Every facet of engineering contributes to enhancing almost every aspect of our lives. As technology continues to evolve, the demand for skilled engineers will only increase. Therefore, it is essential that STEM education system adapts to the needs of today's digitized, diversified, and rapidly changing society through an …

Assistive Robotic Platform For Non‐Urgent Household Tasks: A New Design, Amanda Serger, Normandy Tanguilan, Hakki Erhan Sevil

36th Florida Conference on Recent Advances in Robotics

Humans overcome minor household inconveniences daily without fully recognizing how challenging these tasks could be for individuals such as elderly people or people with disabilities. Those people often times struggle to complete tasks, for instance opening a door or reaching for an item, leading them to rely on caregivers for help. During the COVID-19 pandemic, this caregiver support becomes an unsafe and unreliable solution that can result in a greater risk, thus the need for another solution arises: robotic technology. Recent developments in the robotics field have paved the way for this research, aiming to design a home assistance robot …

Reinforcement Learning And Place Cell Replay In Spatial Navigation, Chance Hamilton, Pablo Scleidorovich Phd, Alfredo Weitzenfeld Phd

36th Florida Conference on Recent Advances in Robotics

In the last decade, studies have demonstrated that hippocampal place cells influence rats’ navigational learning ability. Moreover, researchers have observed that place cell sequences associated with routes leading to a reward are reactivated during rest periods. This phenomenon is known as Hippocampal Replay, which is thought to aid navigational learning and memory consolidation. These findings in neuroscience have inspired new robot navigation models that emulate the learning process of mammals. This study presents a novel model that encodes path information using place cell connections formed during online navigation. Our model employs these connections to generate sequences of
state-action pairs to …

Biologically Inspired Multi-Robot System Based On Wolf Hunting Behavior, Zachary Hinnen, Chance Hamilton, Alfredo Weitzenfeld

36th Florida Conference on Recent Advances in Robotics

Studies involving the group predator behavior of wolves have inspired multiple robotic architectures to mimic these biological behaviors in their designs and research. In this work, we aim to use robotic systems to mimic wolf packs' single and group behavior. This work aims to extend the original research by Weitzenfeld et al [7] and evaluate under a new multi-robot robot system architecture. The multiple robot architecture includes a 'Prey' pursued by a wolf pack consisting of an 'Alpha' and 'Beta' robotic group. The Alpha Wolf' will be the group leader, searching and tracking the 'Prey.' At the same time, the …

Programming By Demonstration Using Learning Based Approach: A Mini Review, Atul Acharya, Rajiv Dubey, Redwan Alqasemi

36th Florida Conference on Recent Advances in Robotics

Wheelchair-mounted robotic arms are used in rehabilitation robotics to help physically impaired people perform ADL (Activity of daily living) tasks. However, the dexterity of manipulation tasks makes the teleoperation of the robotic arm challenging for the user, as it is difficult to control all degrees of freedom with a handheld joystick or a screen touch device. PbD (Programming by demonstration) allows the user to demonstrate the desired behavior and enables the system to learn from the demonstrations and adapt to a new environment. This learned model can perform a new set of actions in a new environment. Learning from a …

Comparing Probabilistic Planning Success On Three Types Of Robots: Wheeled, Legged, And Underwater, Daniel Griessler, Josias Moukpe, Braidan Duffy, Akil Hosang, Blake Janes, Omar Jebari, Kourtnee Fernalld, Erbene De Castro, Humberto Rivera, William Stern, Badria Alfurhood, Akram Alghanmi, Marius Silaghi

36th Florida Conference on Recent Advances in Robotics

We compare the relevance of POMDP graphical models to addressing a given common task, the autonomous navigation, in mobile robotics, for robots in three different environments: legged walking, wheeled, and underwater robots. Principled approaches to the implementation of Intelligent robots in realistic environments with uncertainty exploit probabilistic models. The use of graphical models increases tractability and verifiability of probabilistic reasoning. Our robots face similar localization problems of passing by three doors on a corridor in a building, respectively, for the underwater case, of passing by three barrels in a pool. All the three robots are equipped solely with noisy sonars …

Design, Fabrication, And Verification Of A Robot Leg For Multimodal Locomotion, Cameron Ryals, Ben Labiner, Justin Cheesborough, Carlos Sanchez-Sarmiento, Dane Seal, Ashley Chase

36th Florida Conference on Recent Advances in Robotics

In robotics, there is a variety of general forms of locomotion for a quadruped. This paper focuses on the design challenges for three of the most common forms: walking, climbing, and swimming. Many robots have been designed that can perform a combination of these modalities with the use of interchangeable parts. However, there is limited research on a design that incorporates the requirements of compliance and robustness for walking on rugged terrain, multiple attachment points for climbing, and sufficient drag properties for swimming and walking through resistive media within a singular leg configuration. In this paper, the design, fabrication, and …

Flexible Magnetic Skin Sensor Array For Torsion Perception, Lucja Stawikowska, Erik D. Engeberg

36th Florida Conference on Recent Advances in Robotics

Prosthetic hands help upper limb amputees and people who were born without hands. Currently, these prostheses are rather rudimentary and do not provide adequate sensing capabilities compared to a human hand. People use their natural hands to perceive complex tactile phenomena such as shear and torsion using thousands of mechanoreceptors in their fingertips. The capability to detect torsional loads at the fingertips is a notable gap in prosthetic hand sensation. Flexible tactile sensors are a promising new technology that would be ideal for prosthetic hands since they allow for stretching and movement like human skin without damage to the sensor. …

Nckri Symposium 9: Proceedings Of The 17th Multidisciplinary Conference On Sinkholes And The Engineering And Environmental Impacts Of Karst Full Proceedings, Nckri

Sinkhole Conference 2023

No abstract provided.

Conference Award Ceremony*, Office Of High Impact Practices And Undergraduate Research

Undergraduate Research Conference

No abstract provided.

Object Detection Accuracy Enhancement In Color Based Dynamic Sorting Using Robotic Arm, Luke Fina, Tabatha Mascarenhas, Cody Smith, Hakki Erhan Sevil

36th Florida Conference on Recent Advances in Robotics

In this study, our aim is to develop a robust sorting algorithm to classify and organize objects in terms of their colors using a robotic arm. Developed code allows the robotic arm to retrieve items from a moving conveyor belt, and sort them into corresponding bins ac- cording to their color. The three main parts of the system are the conveyor belt, the robotic arm, and the camera that is used for ob- ject detection based on color. Using the developed system, red, green, and blue objects are detected and localized by the algorithm and the robotic arm successfully picks …

On The Design Of A Single Degree Of Freedom Upper Arm Rehabilitation Robot With Its Gamification Methodology, Mertcan Kocak, Erkin Gezgin

36th Florida Conference on Recent Advances in Robotics

Throughout human life, neurological disorders may occur in body parts with accidents or other biological factors by destroying nerve commands. Stroke is one of the main causes among these disorders. Increase in stroke cases causes to increase requirement in continuous and efficient repetitive physiotherapy exercises that have great benefits in restoring functional losses by retraining motor movements. As a result, demand in treatments increases in parallel and it needs to be fulfilled in a simplest and fastest way. Given these facts, current study focuses on a simple low cost single degree of freedom tip follower rehabilitation system that focuses on …

Optimization Techniques Using Modefrontier - Process Review, Kumar Yogesh Shah, Hakeem Cumberbatch, Lucas Etchart

36th Florida Conference on Recent Advances in Robotics

Optimization is a vital tool to advance the world around us. In order to optimize a variety of design problems, the industry implements the use of a commercial optimization software named modeFRONTIER. It was initially developed as a collaboration between universities, research companies, and private industries in Europe. This software can streamline the design process via its workflow-based environment, multi-objective optimization algorithms, and post-processing tools delivering statistical analysis and data visualization. This provides engineers and researchers with the necessary information for effective decision making in the design process. modeFRONTIER can be coupled with other design tools such as Computer Aided …

Refinement Of Probabilistic Models For The Nao Robot In A Labyrinth, Akram Alghanmi, Samantha Eaton, Kleanthis Zisis Tegos, Sagar Vilas Jagtap, Godwyll Aikins, Neda Keivandarian, Ran Bi, Marius Silaghi

36th Florida Conference on Recent Advances in Robotics

A framework based on a Probabilistic Model for the moving be- havior of the NAO humanoid robot in the environment given by 20in × 20in vinyl maze cells was proposed in a recent work of our group and here it is further expanded with additional support data and model refinements. We also contribute additional tests supporting evidence that it is possible to exploit a public NAO sensor database made recently available, to build a sample probabilistic model for walking and turning in a controlled vinyl maze. The probabilistic model is a new and powerful representation of related phenomena based on …

Experimental Evaluation Of Proximal Policy Optimization And Advantage Actor-Critic Rl Algorithms Using Minigrid Environment, Wen-Chung (Andy) Cheng, Zhen Ni, Xiangnan Zhong

36th Florida Conference on Recent Advances in Robotics

This paper studies the extended experiments of agent-environment interactions of recent reinforcement learning (RL) algorithms, i.e., Proximal Policy Optimization (PPO) and Advantage Actor Critic (A2C). In addition to the evaluation of accumulated rewards in the MiniGrid environment, this work also assesses the learned value tables and others. The experiment platform is expanded with arbitrary shape of mazes, customized training scheme, and the average computation from different initial seeds. The key RL formulas and hyperparameters are explicitly discussed with MiniGrid settings. From the obtained results, the conclusion provides the strengths and weaknesses of neural network implementation for RL methods. This …

The Effect Of Hidden Geometry On The Signal Characteristics In Additive Manufactured Parts, Alireza Modir, Ibrahim Tansel

36th Florida Conference on Recent Advances in Robotics

Structural health monitoring (SHM) has been used in various engineering sectors such as aerospace and civil engineering applications for reducing maintenance costs and to operate the system safely by detecting faults in the system. Additive manufacturing (AM) was used primarily for prototyping but recently many parts are produced for actual use to benefit from the layer by layer part generations. AM can generate very complex geometries which cannot be manufactured by convention manufacturing. The internal hidden geometry of an AM part can be designed to simplify the defect location estimation by using SHM methods. A PLA cross-shaped part was designed …

On The Conceptual Design Of A Macro Micro Robot Manipulator For Cochlear Microrobot Operations: A Case Study On Cochlea Localization, Alp Emre Yasar, Tugrul Uslu, Erkin Gezgin, Levent Cetin

36th Florida Conference on Recent Advances in Robotics

Utilization of robotics in medical sciences has initiated many treatment opportunities that are otherwise impossible to be applied by conventional procedures. Thanks to rapid technological developments on the related field, new approaches as the utilization of microrobots in surgical operations have been started to be proposed for a variety of medical cases. One of the recent scenarios amongst them can be given as the idea of manipulating tetherless microrobot inside the cochlea in order to provide remedy for inner ear poblems. Considering related literature, current study tries to briefly introduce conceptual design of a macro-micro surgical robot manipulator that will …