group

What campus are you from?

Daytona Beach

Authors' Class Standing

Andy Garcia, Junior Nicholas Dolton, Sophomore Salvatore M. Pizzurro, Sophomore Mario Gutierrez, Sophomore Christian MacKay, Sophomore Braden Amoruso, Sophomore Chirag Kumar, Sophomore Jarret Usui, Sophomore Lingyuan Meng, Freshman

Lead Presenter's Name

Andy Garcia

Faculty Mentor Name

Dr. Sergey Drakunov

Abstract

Harmful waste is prevalent all over the world, especially in publicly accessible tourist locations such as here in Daytona Beach. Sustainable Environment Autonomous Litter-Remover (SEAL) is intended to be a fully autonomous, all-terrain waste-sifting robot. SEAL’s main goal is to locate, navigate to, and remove harmful waste within GPS-inaccurate environments, and the environment we’ll be operating in will be sandy beaches near the coast. Using this environment for operation comes with the prominent challenge of localization, as there is a lack of significant features within the area and the area’s locale; therefore, localization tends to be extremely challenging as the features that are present and can be used are untraditional and further the extent of the challenge. The need to localize within an environment lacking distinctive features, which has all these factors like ours, proposes the need to use sensor fusion techniques to localize; however, the combination of autonomy, sensor fusing, and the processes required for localization can be extremely strenuous and computationally costly, especially on a small rover robot. The usage of GPS data, though inaccurate, can be used together with visual data to effectively utilize larger identifiable static features located on buildings along the coast. To effectively localize, we use simple computer vision techniques. These techniques are utilized and applied to a specified search area, and afterward, the image results are applied to a YoloV11 classifier model, allowing for validation of the image and features detected. Allowing for effective localization within the environment and minimizing the computational costs of the onboard computer.

Did this research project receive funding support from the Office of Undergraduate Research.

No

Share

COinS
 

Sustainable Environmental Autonomous Litter-Cleaner Phase I (SEAL)

Harmful waste is prevalent all over the world, especially in publicly accessible tourist locations such as here in Daytona Beach. Sustainable Environment Autonomous Litter-Remover (SEAL) is intended to be a fully autonomous, all-terrain waste-sifting robot. SEAL’s main goal is to locate, navigate to, and remove harmful waste within GPS-inaccurate environments, and the environment we’ll be operating in will be sandy beaches near the coast. Using this environment for operation comes with the prominent challenge of localization, as there is a lack of significant features within the area and the area’s locale; therefore, localization tends to be extremely challenging as the features that are present and can be used are untraditional and further the extent of the challenge. The need to localize within an environment lacking distinctive features, which has all these factors like ours, proposes the need to use sensor fusion techniques to localize; however, the combination of autonomy, sensor fusing, and the processes required for localization can be extremely strenuous and computationally costly, especially on a small rover robot. The usage of GPS data, though inaccurate, can be used together with visual data to effectively utilize larger identifiable static features located on buildings along the coast. To effectively localize, we use simple computer vision techniques. These techniques are utilized and applied to a specified search area, and afterward, the image results are applied to a YoloV11 classifier model, allowing for validation of the image and features detected. Allowing for effective localization within the environment and minimizing the computational costs of the onboard computer.

 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.