TAMUCC Engineering · Senior Design 2025

The autonomous robot
cleaning Texas waterways.

ADDRAR IV is an AI-powered catamaran that detects, navigates to, and collects floating debris — built by five engineering seniors at Texas A&M University Corpus Christi.

HERO PHOTO — Robot in water (16:9)

--kg
Waste Collected
All missions combined
--
Items Logged
GPS + class tagged
--kg
CO₂ Avoided
vs diesel cleanup boat
--
Missions Completed
Fully autonomous
88%
Detection Accuracy
30fps
Real-Time AI
45min
Autonomous Runtime
<$2K
Total BOM Cost

Built and supported at

Robot Photo

About the Project

Built to Clean
Our Waterways

A 4th-generation autonomous surface vehicle

ADDRAR IV is the latest iteration of an autonomous surface vehicle (ASV) built by the Engineering Senior Design team at Texas A&M University Corpus Christi. With 5.25 trillion pieces of plastic debris in the ocean and 269,000 tons floating on the surface, the team developed a sustainable solution for coastal communities.

The system integrates a YOLO11s vision model on a Raspberry Pi 5 with an ESP32 motor controller for real-time debris detection and collection — removing trash from the waterway without human intervention during the mission.

Raspberry Pi 5 (8 GB)
Pi Camera 3 Wide
6× Brushless Motors
ESP32 Controller
Catamaran Hull
Adafruit GPS
3× LiPo Battery Packs
6× 120A ESCs

Core Capabilities

What ADDRAR Does

A purpose-built marine platform combining autonomous navigation, debris detection, and collection into a single deployable unit.

01

AI Debris Detection

Powered by a Raspberry Pi 5 and Pi Camera 3 Wide, the onboard AI vision system identifies floating debris in real time with a wide-angle field of view — distinguishing trash from natural objects on the water surface.

02

Mesh Collection System

Integrated mesh netting between the twin catamaran hulls captures floating debris as the vessel moves forward, retaining collected material without requiring manual retrieval mid-mission.

03

6-Propeller Drive

Six waterproof ring motors with propellers provide omnidirectional thrust, enabling precise maneuvering in tight spaces like marinas, harbors, and coastal inlets.

04

Dual Control Modes

Seamlessly switch between full AI autonomy and manual remote control, allowing operators to intervene for targeted collection or take over in complex scenarios.

05

Catamaran Stability

Twin-hull design provides excellent stability in varying water conditions while creating a natural channel for debris to flow into the collection mesh.

06

Waterproof Electronics

All electronics are housed in sealed enclosures with protected ESC controllers, ensuring reliable operation in marine conditions with splash and spray protection.

AI Vision System

How ADDRAR Sees & Hunts Debris

A trained computer vision model running on a Raspberry Pi 5 processes live video from the Pi Camera 3 Wide — detecting floating debris and autonomously steering the vessel toward it for collection.

Detection & Navigation Pipeline

01

Wide-Angle Capture

The Pi Camera 3 Wide captures a continuous video stream with a 120° field of view, scanning the water surface ahead and to both sides of the vessel.

02

Frame Processing on RPi 5

Each frame is fed into the Raspberry Pi 5 where the trained AI model runs inference in real time, analyzing every frame for debris objects against the water background.

03

Object Detection & Classification

The model draws bounding boxes around detected debris, classifying objects by type (plastic, wood, foam, mixed waste) and assigning a confidence score.

04

Autonomous Navigation

Detected debris coordinates are passed to the navigation system, which steers all six propellers to intercept and collect the target using proportional control.

Model Performance Metrics
88.4%
mAP@0.5
62.1%
mAP@0.5:0.95
91.2%
Precision
85.7%
Recall
~33ms
Inference Time
2,847
Training Images
Vision Hardware
ComputeRaspberry Pi 5 (8 GB LPDDR4X)
Storage128 GB microSD
OS64-bit Linux
CameraPi Camera 3 Wide — 25×24 mm, 0.022 lbs
FrameworkRoboflow + ONNX
ModelYOLO11s / ONNX
Training & Dataset

The detection model was trained on Google Colab using a custom Roboflow dataset of labeled aquatic debris images, then exported as ONNX and deployed to the Raspberry Pi 5.

Water-specific augmentation — surface glare simulation, rotation, perspective warp
Class-balanced training across 5 debris categories with MixUp to reduce class confusion
Exported as FP32 and INT8 ONNX — INT8 provides 2–3× faster inference on Pi 5
AI outputs directly control adaptive motion via ESP32

IoT & Telemetry

Live Data & Monitoring

ADDRAR streams real-time telemetry data from its onboard sensors via IoT, giving operators full visibility into the vessel's status, environment, and mission progress.

Live Data Telemetry

Battery health & voltage, debris collected, boat speed, and GPS location streamed live — updates every 2 seconds and accessible from any network.

Live Graphs & Excel Report

Debris collected and boat speed displayed as live graphs on the dashboard. Full data export available as an Excel report for post-mission analysis.

Cloudflare Tunnel / T-Mobile 4G

Dashboard is securely exposed via Cloudflare Network Tunnel over T-Mobile 4G coverage, enabling remote access from outside the local network.

Live Video Feed

Stream real-time video from the Pi Camera 3 Wide directly to the dashboard — first-person view with live debris detection overlay.

Live Telemetry Preview

Live
87%
Battery
22.2V
Voltage
2.1m/s
Boat Speed
3
Debris Count
27°N
GPS Location
12:04
Clock Time
Dashboard Live

Access the Control Interface

The live dashboard runs on the robot's Raspberry Pi. When the robot is powered on and connected, operators can stream video, view telemetry, and send commands.

Video30fps live stream
Update RateEvery 2 seconds
NetworkCloudflare Tunnel
ExportExcel data report

Environmental Intelligence

Time-Evolving Pollution Heatmap

Every detected item is logged with GPS coordinates, debris class, and timestamp. The dashboard renders a time-evolving pollution heatmap — scrub the slider to watch debris accumulate across a mission, filter by debris type, and compare pollution patterns across missions and seasons.

Harbor Pollution Map — Corpus Christi Bay
Live Data

NO DEBRIS DATA YET — COMPLETE A MISSION TO POPULATE

Mission Time

Predictive Intelligence

Where Debris Will Accumulate

Using real-time wind and weather data from NOAA, combined with historical debris collection patterns, ADDRAR predicts where debris is most likely to concentrate — so missions can be planned proactively.

Predicted Accumulation Zones — Next 24h
LOADING WIND...
HIGH PROBABILITY
MODERATE
LOW
Wind
--
--
Gusts
--
peak
Tide
--
--
Risk Level
--
debris accumulation

Loading weather data...

Impact & Applications

Why ADDRAR Matters

Autonomous debris removal creates measurable impact across environmental, municipal, and maritime domains.

Environmental Protection

Continuous autonomous deployment removes plastic and waste before it sinks, breaks down, or harms marine life — operating in areas that are difficult or dangerous for human crews.

  • Collected 94% of test debris in 12-minute pool trial
  • Zero emissions — electric ring-motor propulsion
  • Detects marine life vs debris at 91% accuracy

City & Municipal Use

City stormwater systems and urban waterways accumulate debris rapidly after rain events. ADDRAR provides a cost-effective automated cleanup alternative to manual crew dispatch.

  • Under $2,000 per unit — fraction of commercial cost
  • Automated stormwater drain response
  • Scales to multi-vessel coordination

Port & Marina Operations

Harbors and marinas require constant debris management to protect vessel hulls, propellers, and infrastructure. ADDRAR handles routine surface debris autonomously.

  • Fits between boats — 60 cm beam width
  • 38-min continuous coastal test run validated
  • Keeps marina channels clear without crew dispatch

A Deployable Solution for Coastal Texas

Developed and tested in the coastal environment of Corpus Christi — ADDRAR IV is purpose-built for the waterways it serves.

45min
Autonomous Runtime
<5min
Battery Swap
4th
Generation

Competitive Landscape

ADDRAR IV vs Commercial Alternatives

Commercial autonomous cleanup vessels like the RanMarine WasteShark+ Pro retail for $40,000+. ADDRAR IV delivers comparable capability — plus features the commercial leader has not shipped — at under $2,000 in parts.

Feature WasteShark+ Pro ADDRAR IV
Autonomous navigation
AI debris classificationHardware only — not shipped✓ Fully implemented
Debris-type breakdown (live)✓ 4 classes
Pollution heatmapStatic✓ Time-evolving
Wildlife-aware routing✓ Planned
Live telemetry dashboard
Open data exportExcelCSV / JSON / GeoJSON
Hot-swap battery✓ (<5 min)
Unit cost$40,000+< $2,000 BOM

Test Results

Performance & Metrics

Results from controlled pool trials and coastal water testing sessions conducted by the TAMUCC team.

≥20min
Required Runtime
15lbs
Debris Capacity
140m
RC Operating Range
6
Drive Propellers
System Capability Assessment
Detection
88%
Navigation
80%
Collection Rate
75%
Stability
92%
Comms Uptime
95%

Technical Specifications

Hardware & Characteristics

Full technical specs and bill of materials for ADDRAR IV.

PlatformCatamaran ASV (twin-hull)
ComputeRaspberry Pi 5 (8 GB LPDDR4X, 128 GB microSD)
CameraPi Camera 3 Wide — 25×24 mm, 0.022 lbs
Propulsion6× HobbyStar 3660 Brushless, 1550 KV, 50A max
ESC120A, 6S compatible (×6)
Propeller3-blade aluminum, D=46 mm (1.81 in), P/D=1.4
Motor ControllerESP32 via iBus (Arduino Core)
Battery — Propulsion3× Turnigy 6S LiPo 22.2V 20Ah 12C (XT-90)
Battery — Electronics1× Turnigy 2S LiPo 2.2Ah 40C (XT-60)
Remote ControlFlySky FS-i6X, 2.4 GHz, 150 m range
GPSAdafruit GPS Module
CommunicationCloudflare Tunnel / T-Mobile 4G
AI ModelYOLO11s / ONNX via Roboflow
Hull MaterialAluminum structure + 3D printed parts
Length61.85 in
Width49.88 in
Height23.75 in
Max Weight<70 lbs
Debris CapacityUp to 15 lbs
RC Range140 m perimeter
Min Runtime≥20 minutes
Est. Cost~$1,645 (electronics, motors, batteries) / $2,500 max
Bill of Materials
ComponentDescriptionQty
RPi 5 (8 GB)Main compute board, 128 GB microSD1
Pi Cam 3WWide-angle vision camera1
HobbyStar 3660Brushless motor, 1550 KV, 50A max6
ESC 120A6S electronic speed controller6
Propeller3-blade aluminum, 46 mm, P/D=1.46
6S LiPo 20AhTurnigy propulsion battery (22.2V, 12C)3
2S LiPo 2.2AhTurnigy electronics battery (40C)1
ESP32Motor controller via iBus + Arduino1
FlySky FS-i6X2.4 GHz RC transmitter & receiver1
Adafruit GPSGPS positioning module1
Voltage Divider22.2V → 3.3V for ESP32 battery read1

Engineering Lineage

4 Generations of Iteration

ADDRAR is a multi-year TAMUCC research lineage. Each generation incorporates lessons learned from previous trials.

I

ADDRAR I

Manual-control proof of concept. Validated hull form and propulsion.

II

ADDRAR II

Added telemetry + GPS waypoint following. Introduced collection net.

III

ADDRAR III

First vision system. Basic object detection with fixed-rule heuristics.

IV

ADDRAR IV — current

Full YOLOv8 AI classification, 6-propeller omnidirectional drive, live IoT dashboard, and autonomous mission planning.

The Team

Meet the Engineers

Senior design team at Texas A&M University Corpus Christi, College of Engineering & Computer Science.

Nathan Favier
Nathan Favier
Project Manager
Mechanical Engineering
Coordinated a 5-person engineering team across mechanical, electrical, and software workstreams. Owned systems integration between the RPi 5 compute core, motor controllers, and the live telemetry dashboard.
Joshua Hernandez
Joshua Hernandez
Mechanical Engineer
Mechanical Engineering
Designed and fabricated the twin-hull catamaran structure through 4 SolidWorks iterations. Validated buoyancy, stability, and waterproofing in pool trials.
Connor Lively
Connor Lively
Mechanical Engineer
Mechanical Engineering
Engineered the 6-propeller ring-motor propulsion layout and custom ESC integration. Tuned PWM control logic to balance thrust with maneuverability in tight harbor conditions.
Zadok Villarreal
Zadok Villarreal
Mechanical Engineer
Mechanical Engineering
Built the IoT telemetry pipeline, the live operator dashboard, and the autonomous navigation control loop. Implemented GPS waypoint following, real-time video streaming, and mission data logging.
Brayden White
Brayden White
Mechanical Engineer
Mechanical Engineering
Designed the integrated mesh debris collection system between the hulls. Validated passive capture efficiency across multiple debris types in controlled pool testing.
Faculty Mentor
Dr. Ruby
ENTC 4350 — Project Progress  ·  Texas A&M University Corpus Christi

Common Questions

Frequently Asked

How long can ADDRAR IV run on a single charge?

Approximately 45 minutes of continuous autonomous operation on our current LiPo battery pack. Battery swap takes under 5 minutes.

What types of debris can it detect?

The onboard YOLO model is trained on multiple classes including plastic bottles and bags, foam, and mixed waste. It was trained on thousands of labeled images captured in local coastal conditions.

Can it operate in saltwater?

Yes. All electronics are sealed in waterproof enclosures, and the hull and hardware are selected for saltwater compatibility.

What happens if the AI misidentifies something?

The confidence threshold is tuned conservatively to minimize false positives. Operators can also intervene in real time via the dashboard — the vessel supports seamless switching between autonomous and manual control.

How much does it cost to build?

Under $2,000 in parts (full BOM on the Specs page). Commercial alternatives like the RanMarine WasteShark+ Pro retail for $40,000+.

How does it avoid collisions?

Proportional control using GPS, IMU data, and vision-based detection. The system slows and pauses when obstacles are detected in its path. Wildlife avoidance is also being trained into the AI model.

Live System Access

Robot Dashboard

Access the live control and monitoring interface. The dashboard runs on the robot's Raspberry Pi — only available when the robot is powered on and connected.

How Dashboard Access Works

The robot streams live video, telemetry, and accepts remote commands via a Cloudflare Tunnel hosted on the onboard Raspberry Pi 5. When the robot is on, the dashboard is live at dashboard.addrarlivevideo.com.

If the Pi is powered off or disconnected, the dashboard will simply be unavailable — the info site remains online regardless.

Note: Dashboard access is restricted to authorized operators. Select your vessel and enter the access password to proceed. Contact your team lead if you need credentials.
Secure Access Portal
Incorrect password or no vessel selected.
Opens dashboard.addrarlivevideo.com — if the Pi is offline, the page will fail to connect. This is expected.