Significance of Study
This research addresses a critical challenge in the field of automation: the inevitable wear and tear of machinery which necessitates costly and time-consuming maintenance and repairs. The significance of this project lies in its potential to revolutionize the approach to machine maintenance, shifting from reactive to proactive measures that can minimize both the financial burden and downtime associated with traditional preventative maintenance and improve the reliability and efficiency of automated systems.

Subject Background
Machinery in automated systems is prone to degradation over time, leading to operational inefficiencies and potential failures. Traditional maintenance strategies are often reactive and can be prohibitively expensive and disruptive. The theoretical foundation of this research is built upon the premise that machine learning models, particularly those capable of detecting anomalies, can play a pivotal role in identifying and predicting potential issues before they result in significant downtime or costly repairs. Prior explorations into models such as long short-term memory (LSTM) recurrent neural networks and k-nearest neighbors (KNN) classifiers have provided valuable insights, yet they fall short in accurately and reliably identifying anomalies compared to the isolation forest model.

Methodology
The research focuses on the development and testing of an isolation forest machine learning model. This model will analyze data points from sensors embedded in automation machinery to identify potential anomalies indicative of wear or failure. Comparative analysis will be conducted with other machine learning models, such as LSTM recurrent neural networks and KNN classifiers, to evaluate the efficacy and reliability of the isolation forest model in real-world scenarios. The study will also investigate the challenges of integrating machine learning models into existing automation systems, particularly the limitations of programmable logic controllers and the capacity of attached computers to process and act on the data in real time.

Preliminary Findings
While the research is ongoing, preliminary findings suggest that the isolation forest model shows promise in accurately detecting anomalies that precede mechanical failures. Expected findings include a detailed analysis of the model’s performance compared to other machine learning approaches, highlighting its superiority in specific contexts of anomaly detection.

Poster Presentation

Session 3

2:45pm – 4:00pm
Grand Salon

Computer Science

In the rapidly evolving landscape of software development, integrating advanced AI capabilities directly into development environments represents a transformative approach to enhancing engineering efficiency and productivity. This research proposes a novel integration of OpenAI’s ChatGPT and Meta’s Llama 2 AI models into the Visual Studio Code environment, aiming to redefine traditional coding practices. By harnessing the complementary strengths of ChatGPT’s natural language processing and Llama 2’s advanced modeling capabilities, this initiative seeks to provide unprecedented code assistance, including automated code generation, real-time debugging, and instant documentation.
The methodology encompasses a detailed strategy for accessing and utilizing the APIs of both AI technologies, setting up a conducive development environment, and crafting a seamless integration framework that embeds these AI assistants within the developers’ workflow. Key phases include securing API access, environment preparation, development of the integration using appropriate programming languages, extensive testing and debugging, and thorough documentation for adoption and maintenance. The expected outcomes include significantly enhanced coding efficiency, superior code quality through deep AI insights, and notable reductions in development time and costs.
This integration not only positions developers at the forefront of AI-assisted coding practices but also paves the way for future innovations in software engineering. The anticipated findings and insights from this research aim to showcase the synergistic potential of combining multiple AI models within development environments, offering a blueprint for the next generation of software development tools.

Poster Presentation

Session 1

9:15am – 10:30am
Grand Salon

Computer Science

The Sawyer robot represents a pioneering leap in robotics, poised to redefine household tasks through the fusion of virtual reality (VR) and computer vision. Its six degrees of freedom allow it a wide range of motion, and with future versions of other humanoid robots currently being developed this proof of concept will help set the groundwork for future software development.
In its current stage Sawyer cannot currently use its on-board camera system for anything more than basic object recognition. This leaves room for situations where a new unseen and unexpected object shows up in Sawyers range of motion. This is where the Optitrack motion capture camera system comes into play, which allows you to place cameras around an environment and allow you to track objects. Integrating this system with Sawyer will give Sawyer the ability to see a 360-degree field of view along with accurate depth detection which would exceed that of 2D videos.
Our goal in this project would be to combine Sawyer, Optitrack and Artificial Intelligence to allow Sawyer to see and react to its environment and be able to operate autonomy to tasks that it is given. We have primarily found information on these topics though forums dedicated to software systems, and other robotics related forums on computer vision and its integration with robots.   To that end we will also be working off Summer Surf Research done last year in 2023 by Sameeh Olipani, Alejandro Antonio and myself where we had success in allowing Sawyer to perform a pick and place action and had it place wooden planks to form a box. To expand upon this research, our next step, will be streaming the Opitrack information from a windows virtual machine to a Linux system that will then integrate the data into ROS so that Sawyer and other programs can utilize the information properly. We are currently in the process of transforming this data into something Sawyer can utilize by writing custom scripts in Python that helps to transform the data into a format readable by Sawyer through the SDK (software development kit) supplied with the robot.

Poster Presentation

Session 1

9:15am – 10:30am
Grand Salon

Computer Science