Title: Autonomous System for Identifying and Capturing Floating Waste

Luis F. W. Batista

Ph.D. Student in Computer Science

School of Interactive Computing

Georgia Tech-Europe

Date: 30th April, 2025

Time: 10:00–11:30 am Eastern (16:00-17:30 CEST)

Location: Virtual

Microsoft Teams Need help?

Join the meeting now

Meeting ID: 282 920 901 69

Passcode: SG27gj2J

Committee:

Dr. Cédric Pradalier (Advisor) - School of Interactive Computing - Georgia Institute of Technology

Dr. Seth Hutchinson (Co-advisor) - School of Interactive Computing - Georgia Institute of Technology

Dr. Sehoon Ha - School of Interactive Computing - Georgia Institute of Technology

Dr. Harish Ravichandar - School of Interactive Computing - Georgia Institute of Technology

Abstract

Plastic pollution in aquatic environments presents a pressing ecological issue. This thesis develops an autonomous system for detecting and collecting floating waste, integrating advanced visual perception, reinforcement learning-based control, with field-tests validation. Key contributions include the use of polarimetric imaging to improve perception on reflective water surfaces, and a robust reinforcement learning framework for navigation that accounts for real-world hydrodynamics. The perception and control components are combined into a complete pipeline, validated through extensive simulation and real-world field trials to demonstrate the system's effectiveness and potential for scalable environmental cleanup applications