Sony Pixel Power calrec Sony

Waterways Wonder: Clearbot Autonomously Cleans Waters With Energy-Efficient AI

17/10/2024

What started as two classmates seeking a free graduation trip to Bali subsidized by a university project ended up as an AI-driven sea-cleaning boat prototype built of empty water bottles, hobbyist helicopter blades and a GoPro camera.

University of Hong Kong grads Sidhant Gupta and Utkarsh Goel have since then made a splash with their Clearbot autonomous trash collection boats enabled by NVIDIA Jetson.

We came up with the idea to clean the water there because there are a lot of dirty beaches, and the local community depends on them to be clean for their tourism business, said Gupta, who points out the same is true for touristy regions of Hong Kong and India, where they do business now.

Before launching Clearbot, in 2021, the university friends put up their proof-of-concept waste collection boat on a website and then just forgot about it, he said, starting work after graduation. A year later, a marine construction company proposed a water cleanup project, and the pair developed their prototype around the effort to remove three tons of trash daily from a Hong Kong marine construction site.

They were using a big boat and a crew of three to four people every day, at a cost of about $1,000 per day - that's when we realized we can build this and do it better and at lower cost, said Gupta.

Plastic makes up about 85% of ocean litter, with an estimated 11 million metric tons entering oceans every year, according to the United Nations Environment Programme. Clearbot aims to remove waste from waterways before it gets into oceans.

Cleaning Waters With Energy-Efficient Jetson Xavier Clearbot, based in Hong Kong and India, has 24 employees developing and deploying its water-cleaning electric-powered boats that can self-dock at solar charging stations. We believe that humanity's relationship with the ocean is sort of broken - the question is can we make that better and is there a better future outcome? We can do it 100% emissions-free, so you're not creating pollution while you're cleaning pollution. Sidhant Gupta, co-founder of Clearbot

The ocean vessels, ranging in length from 10 to 16 feet, have two cameras - one for navigation and another for waste identification of what boats have scooped up. The founders trained garbage models on cloud and desktop NVIDIA GPUs from images they took in their early days, and now they have large libraries of images from collecting on cleanup sites. They've also trained models that enable the Clearbot to autonomously navigate away from obstacles.

The energy-efficient Jetson Xavier NX allows the water-cleaning boats - propelled by battery-driven motors - to collect for eight hours at a time before returning to recharge.

Harbors and other waterways frequented by tourists and businesses often rely on diesel-powered boats with workers using nets to remove garbage, said Gupta. Traditionally, a crew of 50 people in such scenarios can run about 15 or 20 boats, estimates Gupta. With Clearbot, a crew of 50 people can run about 150 boats, boosting intake, he said.

We believe that humanity's relationship with the ocean is sort of broken - the question is can we make that better and is there a better future outcome? said Gupta. We can do it 100% emissions-free, so you're not creating pollution while you're cleaning pollution.

Customers Harnessing Clearbot for Environmental Benefits Kingspan, a maker of building materials, is working with Clearbot to clean up trash and oil in rivers and lakes in Nongstoin, India. So far, the work has resulted in the removal of 1.2 tons of waste per month in the area.

Umiam Lake in Meghalaya, India, has long been a tourist destination and place for fishing. However, it's become so polluted, that areas of the water's surface aren't visible with all of the floating trash.

The region's leadership is working with Clearbot in a project with the University of California Berkeley Haas School of Business to help remove the trash from the lake. Since the program began three months ago, Clearbot has collected 15 tons of waste.

Mitigating Environmental Impacts With Clearbot Data Clearbot has expanded its services beyond trash collection to address environmental issues more broadly. The company is now assisting in marine pollution control for sewage, oil, gas and other chemical spills as well as undersea inspections for dredging projects, examining algae growth and many other areas where its autonomous boats can capture data.

Unforeseen to Clearbot's founders, they have discovered that the data about garbage collection and other environmental pollutants can be used in mitigation strategies. The images that they collect are geotagged, so if somebody is trying to find the source of a problem, backtracking from Clearbot's software dashboard on some of the data on findings is a good place to start.

For example, if there's a concentration of plastic bottle waste in a particular area, and it's of a particular type, local agencies could track back to where it's coming from. This could allow local governments to mitigate the waste by reaching out to the polluter to put a stop to the activity that is causing it, said Gupta.

Let's say I'm a municipality and I want to ban plastic bags in my area - you need the NGOs, the governments and the change makers to acquire the data to back their justifications for why they want to close down the plastic plant up the stream, said Gupta. That data is being generated on board your NVIDIA Jetson Xavier.

Learn about NVIDIA Jetson Xavier and Earth-2
LINK: https://blogs.nvidia.com/blog/clearbot-autonomously-cleans-ai/...
See more stories from nvidia

More from Nvidia

30/07/2026

Best in Class: Stream PC Games and Study on the Same Laptop With GeForce NOW

Back to school means balancing assignments, deadlines and downtime. GeForce NOW makes it easy to have it all. With cloud gaming, everyday laptops used for clas...

28/07/2026

Powerful Compute So Compact, It's Clutch - Build AI in Your Hand With NVIDIA Jetson

As a discerning AI investor who values style and substance, Sarah Guo knows this...

27/07/2026

Industry Leaders Unite in Open Secure AI Alliance for AI Safety and Security

Open source software is a critical pillar of the global economy. It underpins cloud computing, financial services, manufacturing, telecommunications, government...

26/07/2026

NVIDIA Harnesses Vera CPU to Speed Up Design of Next-Generation CPUs and GPUs

The complexity of modern chip design continues to grow as engineering teams work to develop increasingly sophisticated CPUs, GPUs and AI systems. To help meet t...

23/07/2026

At AI Summit, South Korea Outlines Its AI Future With NVIDIA and Partners

At this week's AI Summit in San Francisco, South Korean President Jae Myung Lee and some of the country's top business leaders and researchers are meeti...

23/07/2026

GeForce NOW Sets Sail With Path of Exile: Curse of the Allflame' Joining the Cloud

Lock in and load up the cloud. GFN Thursday brings fresh updates and new adventu...

22/07/2026

NVIDIA AI Supercomputer Comes Online at Naval Postgraduate School

NVIDIA founder and CEO Jensen Huang today visited the Naval Postgraduate School in Monterey, California, to commission an NVIDIA DGX GB300 system - bringing one...

22/07/2026

NVIDIA Open Sources First GPU-Accelerated Medical Physics Simulation Framework

Before a healthcare robot can be useful in the real world, it has to learn how the physical world pushes back. Anatomy varies. Instruments bend, press, slip and...

21/07/2026

Built in Fort Worth: Wistron Opens Advanced Manufacturing Plant to Produce NVIDIA AI Systems

The AI era runs on AI infrastructure. Many of these advanced systems are built a...

21/07/2026

Built for Vera Rubin, NVIDIA Spectrum-6 Arrives in Gigascale AI Factories

AI has entered the gigascale era. The world's most advanced AI factories are bringing together hundreds of thousands of GPUs and CPUs to train frontier mod...

21/07/2026

NVIDIA Vera Rubin Driving Performance Per Watt, Lowest Token Cost for Partners Worldwide

NVIDIA Vera Rubin is here, and it's going gigascale. Vera Rubin NVL72 produ...

20/07/2026

At SIGGRAPH, NVIDIA Advances Graphics and Simulation With Agentic and Physical AI

At this year's SIGGRAPH conference, running through Thursday, July 23, in Lo...

20/07/2026

Bristol Myers Squibb Building Life Science Industry's Most Advanced AI Factory on NVIDIA Vera Rubin

Erin Davis calls it the SuperDuperPOD. That's two things in one name: phar...

17/07/2026

NVIDIA Vera Rubin Maximizes Intelligence per Dollar for Post-Training Workloads - a Key Metric for Agentic AI

Think of a professional athlete. What separates elite performers is what happens...

16/07/2026

Sharpen the Sword, Skip the Downloads - Onimusha: Way of the Sword' Is Coming to GeForce NOW

Onimusha: Way of the Sword is coming to GeForce NOW at launch, with the playable...

15/07/2026

NVIDIA Introduces New Jetson Thor Computers to Advance Mainstream Robotics and Edge AI

General-purpose robots and autonomous machines are moving from research labs to ...

15/07/2026

NVIDIA and Japan Bring Full-Stack AI and Robotics to Every Industry

Home to leading manufacturers, robotics pioneers, infrastructure builders and iconic gaming companies, of course, Japan is one of the world's centers of AI ...

14/07/2026

Nemotron Labs: How Open Models Give Enterprises and Nations AI They Can Trust, Control and Customize

Editor's note: This post is part of the Nemotron Labs blog series, which exp...

14/07/2026

Why Performance per Watt Is the Ultimate Metric for AI Infrastructure Efficiency

Power is AI infrastructure's inescapable constraint. How many tokens an AI factory can generate within a fixed power budget determines its revenue and profi...

09/07/2026

GeForce NOW Turns Up the Heat With New GeForce RTX 5080-Powered Toronto Server

This GFN Thursday brings more games, more power and more ways to play on GeForce NOW. The cloud gaming service is expanding with a new GeForce RTX 5080-powere...

08/07/2026

NVIDIA Nemotron Achieves Benchmark-Leading Performance With LangChain Deep Agents Harness

NVIDIA Nemotron 3 Ultra is offering leading performance at lower cost than top c...

07/07/2026

AI Innovators Adopt NVIDIA Vera - Why Max Single-Threaded CPU at Scale Matters

Max single-threaded CPUs at scale are a new category of CPUs built for the agentic AI era. Across the creation and deployment of an agentic system, the CPU is...

06/07/2026

NVIDIA and Hugging Face Bring New Models and Frameworks to LeRobot for the Open Robotics Community

Open source AI has shown how quickly developers can innovate when models, data a...

06/07/2026

How Nations Are Deploying AI for Strategic Priorities

Nations have long invested in domestic infrastructure to advance their economies, protect and use their data, and take advantage of technology opportunities in ...

06/07/2026

How Open Models Are Driving AI Research

Every year, the International Conference on Machine Learning (ICML) reveals where thousands of AI researchers have decided to put their work. This year's ...

02/07/2026

Joyride Through July With 12 Games Coming to GeForce NOW

Summer is heating up - and GeForce NOW is taking players along for the ride. Start the month with Monopoly: Star Wars Heroes vs. Villains, bringing a galaxy fa...

01/07/2026

NVIDIA Unlocks AI Compute at Scale, Inviting Capital Partners to Power the AI Infrastructure Buildout

As AI moves from model development to production inference, compute demand is ac...

30/06/2026

NVIDIA BioNeMo Agent Toolkit Brings Accelerated AI to Life Sciences Researchers in Claude Science

Life sciences has entered an era of computational scale, and for more than a dec...

30/06/2026

How NVIDIA's Inference Software Stack Powers the Lowest Token Cost

As organizations move from AI pilots to production AI factories, infrastructure decisions have shifted from peak chip specifications to cost per token: how many...

30/06/2026

Into the Omniverse: Three Workflows for Improving Vision AI Agent Accuracy With Synthetic Data and Fine-Tuning

Editor's note: This post is part of Into the Omniverse, a series focused on ...

29/06/2026

Claude Meets Blackwell Ultra: Anthropic's Models Now Run on NVIDIA GB300 in Azure

Anthropic's Claude models in Microsoft Foundry - hosted on Microsoft Azure a...

29/06/2026

Open Models, Closed Environments: Palantir Brings Secure AI to US Agencies With NVIDIA Nemotron

Showcasing the importance of open source innovation in American AI, Palantir'...

25/06/2026

The Ultimate Summer Sale Pairing: Steam Sale Meets GeForce NOW Discounts

Summer savings are heating up. From the Steam Summer Sale to GeForce NOW membership discounts, this week's GFN Thursday delivers double the deals and more w...

23/06/2026

NVIDIA and AWS Collaborate to Bring AI to Production at Scale

Building AI systems at scale is demanding, requiring low-latency inference, fast vector search, strong GPU price-performance and infrastructure that can grow wi...

23/06/2026

NVIDIA Powers Over 400 of the World's 500 Fastest Supercomputers

News Highlights: NVIDIA technology runs 81% of the TOP500 and 90% of the systems new to the list. 26 systems on the TOP500 adopted the NVIDIA Grace CPU, up ei...

23/06/2026

How Businesses Are Building Specialized AI They Can Trust

Editor's note: This post is part of the Nemotron Labs blog series, which explores how the latest open models, datasets and training techniques help business...

22/06/2026

NVIDIA Brings Trusted, 24/7 AI Agents to Telecom Operations

Telecom operators have seen remarkable returns from using generative AI to automate network management, customer care and back-office operations. Most of that i...

22/06/2026

Eco Wave Power Turns Waves Into Watts With NVIDIA AI Infrastructure and Digital Twins

The next era of AI will not be defined by compute alone. Its growth will be dete...

22/06/2026

NVIDIA Vera CPU Opens the Way for Agentic Scientific AI at Los Alamos National Laboratory

Mission, Vision and Veritas - new Los Alamos National Laboratory (LANL) supercom...

22/06/2026

From Materials Simulation to Experimental Astronomy, New NVIDIA AI Software Unlocks Scientific Discoveries

At the ISC conference running in Hamburg this week, NVIDIA is introducing new so...

22/06/2026

NAIRR Science Program Reshapes Scientific Research, Powered by NVIDIA AI Infrastructure

For the past two years, the U.S. National Science Foundation's National Arti...

22/06/2026

At ISC, JUPITER Shows What Exascale Science Looks Like

JUPITER, Europe's first exascale supercomputer at Germany's Forschungszentrum J lich, runs on NVIDIA Grace Hopper Superchips and NVIDIA Quantum-X800 Inf...

21/06/2026

Hotter Than a Hot Tub: The 45C Breakthrough to Cool AI's Biggest Machines

Hot tubs sit at about 38 to 40 degrees Celsius, warm enough that most people can only soak for about 15 minutes. NVIDIA's newest AI servers can run their co...

18/06/2026

How FERC's Large-Load Interconnection Actions Help Address Grid Stress, Improve Affordability

In a consequential grid infrastructure decision, the Federal Energy Regulatory C...

18/06/2026

Sync and Stream: GeForce NOW Connects to Members' Game Libraries Across Devices

Play favorite titles from popular game libraries, keep progress synced and jump ...

18/06/2026

At Cannes Lions, NVIDIA Partners Reshape Advertising and Marketing With AI

The digital era gave the advertising and marketing industry speed; the AI era is giving it autonomous operations. For companies building next-generation techn...

17/06/2026

France Advances Europe's AI Future With NVIDIA Technologies

A year ago at NVIDIA GTC Paris at VivaTech, France laid out plans to advance local AI - from new AI factories and national compute capacity to open frontier mod...

16/06/2026

HPE AI Factory With NVIDIA Expands for the Era of Agents

Enterprises are moving agentic AI from proof of concept to production - and the next generation of AI factories are built for the era of agents. At HPE Discove...

16/06/2026

Coherent Breaks Ground on Expanded Texas Facility, Scaling AI's Optical Backbone

AI runs at the speed of light. More and more, that light is made in Texas. Cohe...

16/06/2026

Fastest, Largest, Strongest: NVIDIA Blackwell Sweeps MLPerf Training 6.0

Every breakthrough AI model starts the same way: with a training run. The infrastructure running those training jobs shapes everything: how fast teams can itera...