One step for Homelessness

Around the world, almost 1 million plastic bottles are purchased every minute. If all of the plastic bottles sold in 2018 were gathered in a pile, it would be higher than the world’s tallest building, the Burj Khalifa in Dubai.

What we are going to do with the Plastic bottles?

Deposit your waste plastic bottle and get rewards. This plastic bottle will use to create a temporary shelter for homeless people

Reverse Vending Machine

Homelessness Around the World

A global survey was attempted – by the United Nations – an estimated 100 million people were homeless worldwide. As many as 1.6 billion people lacked adequate housing (Habitat, 2015). In 2021, the World Economic Forum reported that 150 million people were homeless worldwide.

Reason of homelessness

The homelessness and displacement crisis is a multifaceted issue stemming from economic instability, housing Unaffordability, mental health challenges, substance abuse, systemic inequalities, and natural disasters. These factors intersect to leave many individuals and families without stable housing, facing barriers to accessing essential resources and support services. Addressing this crisis requires a comprehensive approach that considers the root causes while providing immediate assistance to those affected.


How might AI be applied to improve the utilization of discarded plastic bottles for the construction of temporary shelters?


Reinforcement Learning Pipeline

Reinforcement learning is a machine learning training method based on rewarding desired behaviors and punishing undesired ones.



The Adaptive Reinforcement model

The shelter should be Adaptable, if today we have 100 bottles of different sizes but tomorrow we have 50 more of different sizes so, using the reinforcement learning algorithm it adapts to the new bottle set.

Reinforcement to Execution

Use of reinforcement-trained brain to create a small prototype of arch use AR and Human intervenstion.

Failed Attempts


Website Link :

GitHub Link: