Using Artificial Intelligence To Achieve Zero Waste

Artificial intelligence technologies can be used to help buildings and spaces track their waste in real-time and engage users by nudging them to correctly sort their waste.

However, this vision has some major challenges:

1. The ever-increasing volume and complexity of waste as a result of the constant increase in commercial consumerism makes it difficult for the public to recycle properly. For instance, a coffee cup will typically have three components (plastic lid, cardboard sleeve, and paper cup) that need to be sorted and disposed three different bins.
2. Differences in recycling guidelines among regions and municipalities which hinder effectiveness of recycling policies as well as the lack of standardization among cities, primarily driven by:
   1. Local haulers’ recycling tech and capabilities.
   2. The current recycling market, i.e, possibility of up-cycling materials.
   3. Frequent manual waste audits conducted by facilities prove to be costly, lengthy, labor-intensive and misleading.

According to a study by the World Bank, 98% of the world’s waste is sent to landfills, dumped into oceans or being incinerated, even though a high majority of daily consumables are recyclable. This is primarily due to the high level of contaminants found in recyclables, making previously clean material practically unrecyclable and financially unmarketable. In Toronto, for every percentage point decreased in contaminated waste can create up to $1 million in recycling cost savings every year, which can be attributed to the management and sorting costs incurred by the waste hauling and collection companies.

Intuitive is a Canadian company which seeks to achieve zero waste through their AI solution, Oscar. According to a benchmarking waste study of a university’s contamination rates and with early Oscar performance in waste diversion, it is approximated that by nudging users to recycle correctly, each Oscar installed in a facility can reduce up to 10 tonnes of waste from being sent to landfill and thus stopping toxic chemicals from seeping into surrounding water tables.

With a vision to empower a zero-waste world, Intuitive is taking its first steps by leading in the development of a state of the art AI system that is robust, lean, and able to efficiently run inference on the edge by integrating embedded systems and sensors.

• Oscar is designed to have an enormous social impact by targeting the issue of public empathy when it comes to recycling at the source and engaging users, by nudging them to separate their waste items at the point of disposal. This is particularly important in places with high traffic flow such as airports, malls, universities etc. It is within such settings that waste disposal is done at a fast pace and without much room for thought.
• Organizations are looking for alternative ways of conducting lengthy, labour intensive, and costly manual waste audits. Buildings will have instant access to Intuitive’s dashboard that reports waste intake through real-time waste analytics.
• Oscar will update in real time and educate the public pertaining to their municipalities’ latest recycling guidelines. With a retrofittable module that is easily attached to any existing waste bins, there is immense opportunity for expansive and effective public education.

Oscar’s AI System leverages Computer Vision and Machine Learning

Oscar recognizes varied items within the hands of users, i.e, a plastic cup, used paper napkins, empty snack chips bag, biodegradable spoon. Through advanced computer vision research and enhanced machine learning algorithms, Oscar is trained to detect partially visible items as well as recognize a variety of body postures of identifiable approaching users.

The main challenge with such algorithms is to facilitate quick edge processing so that Oscar can be as dynamic as possible and make its predictions in real-time. Additionally, data quality is just as important as data quantity to train Oscar effectively; for instance, a coffee cup might look different in a brightly lit food court as compared to a dim office kitchen. Intuitive is building upon its current technology by training the AI systems with thousands of images of waste items held by users in every possible way, emulating the behaviors at places such as a food court, office kitchens etc. This process is designed to ensure that Oscar will be able to run real-time predictions, engaging users in an intuitive and dynamic manner.

Creating AI for social good has the interesting challenge of dealing with social dangers such as detecting faces as people approach the bin. Maintaining the privacy of the public is critical, and it is to this end that Intuitive is continually researching and improving their enhanced machine learning algorithms to anonymize any personally identifiable information. Oscar has been trained to recognize different body movements and poses so that a wide range of users approaching the bin have their faces instantaneously detected and blurred.

Another research opportunity Intuitive is aiming to engage in is how the fill capacity of a waste item such as a coffee cup has the propensity to change the approaching user’s body movements as it will alter the way they hold the coffee cup, for instance. Oscar’s prediction engine is trained to know what the fill levels of the bins are before the waste item has been disposed. Additionally, there will be research done on how to implement different gestures so that Oscar will be adept at recognizing custodial staff when it’s time to empty out the bins.

As a company developing AI for social good, it is important that Intuitive remains social and not cocooned into solitary work. It is to this end that the company aims to partner with sustainability champions that will invite Oscar into their organizations and are keen on implementing a zero waste strategy within their premises. The world is at an opportune moment with cutting edge proprietary technology to solve a global challenge, and Intuitive is diligently working on making Oscar an industry revolutionizing product that will divert waste away from landfills all over the world. With AI deemed the 4th industrial revolution and the waste management industry at a crossroad with the recent global recycling crisis, it seems that waste management is an area where AI will have a positive social impact.

This article was co-authored by Hassan Murad and Yaz How and is a part of RE•WORK’s white paper “AI for Social Good” that you read by clicking here. You can also learn more about RE•WORK’s events and conferences for AI and deep learning. 

Hassan Murad is the CEO & Co-Founder of Intuitive AI where they are developing AI to empower a zero waste world. He was driven by the world’s massive waste problem to begin creating solutions along with co-founder, Vivek Vyas, and divert waste away from landfills, oceans or incineration. His robotics background, that includes working on autonomous submarines, farm-mapping drones, and self-driving cars at Tesla, has inspired him to develop Oscar, AI for Zero Waste. Hassan has won numerous awards recognizing his leadership in innovation and was recently featured on Forbes as the top 5 Entrepreneurs On The Rise in AI. He holds a B.Sc. in Mechatronics from Simon Fraser University and is currently based in Vancouver, BC.

Looking to apply AI for social good? Sign up for more education.

We’ll let you know when we release more educational articles covering beneficial applications of AI for society.

Read the full Rework AI For Social Good whitepaper