Hardware Podcasts

Innovative Waste Recycling: AI and Robotics with Areeb Malik, Co-founder of Glacier

Hardware to Save a Planet · 18 Aug 2022 · 41m · Episode 7

AI in practice: one real use of AI described

What this episode covers

Areeb Malik, co-founder of Glacier, explains how his company uses AI and robotics to automate sorting at Materials Recovery Facilities (MRFs), addressing the industry's labor shortages and contamination issues. He details the technical challenges of computer vision for trash classification and robotic end-effectors, noting that Glacier's custom-designed robots cost 60% less than competitors and offer a payback period of under two years. Malik also discusses the impact of China's 'National Sword' policy on global recycling markets and the growing demand for recycled content driven by legislation and consumer pressure.

AI in practice

Where this conversation describes AI being used to build or deliver a product. Part of the AI in practice tracker.

Engineering & simulationobject detection computer vision model

Glacier trained a neural net on hundreds of thousands of manually tagged images of trash on conveyor belts to identify and classify recyclable items like bottles and cans for robotic sorting.

“we take 100s of 1000s of images of trash on conveyor adults … we manually tag those images … feed that to the model. It can then be trained on that. So if it's seen a 1000 water bowels for odds are, if you show it in a 1000 and 1st it'll be able to identify without hitter seeing it before.”

Speaker 2 · Hear it at 26:10

Most relevant to

early-stage companies

Topics

Mentioned

Companies
Glacier, Facebook, Heirloom Technologies, Ellen MacArthur Foundation, Coke, Nestle
Tools
disk screen

Related episodes from other shows

Other shows on the same ground, closest first.

  • The Robot Report Podcast · 1h 12m

    Inside Glacier's Mission to Modernize Recycling

    Rebecca Hu-Thrams, CEO and co-founder of Glacier, explains how Glacier Robotics builds custom gantry robots to automate material recovery facilities (MURFs), addressing the challenge of sorting diverse, contaminated waste streams with high precision and uptime. She details the company's strategic partnerships with major brands like Amazon and Colgate-Palmolive to use AI data for better packaging design, and highlights their focus on achieving sub-12-month payback periods for recycling facilities. The episode also covers news from Parallax Worlds, which raised $4 million for digital twin simulation, and discusses the broader robotics industry trends including Physical Intelligence's funding and Agile Robots' industrial humanoids.

    Robotics & autonomyMechanical engineering
    8 chapters

  • People of Packaging · 32m

    191 - Will AI help close the gaps in recycling? Apurba Pradhan from Everest Labs

    Apurba Pradhan, head of product and marketing at Everest Labs, explains how his company uses AI and robotics to automate sorting at Material Recovery Facilities (MRFs). He details the inefficiencies of manual labor and semi-precise optical sorters, describing how their system replaces human pickers to improve commodity purity. Pradhan highlights the company's service model, which includes 24/7 monitoring and performance guarantees to ensure ROI and address MRFs' lack of technical staff. The conversation covers the impact of the Chinese National Sword policy on domestic recycling demand and the economic viability of automation in the current market.

    Robotics & autonomyManufacturing partners & offshoring
    6 chapters

  • How I Built This · 32m

    When robots recycle with Matanya Horowitz of AMP Robotics

    Matanya Horowitz, founder and CEO of AMP Robotics, explains how his company uses AI and robotics to automate waste sorting, a sector where only about 35% of US waste is currently recycled. Horowitz details the transition from using mechanical claws to vacuum-based systems to handle sticky contaminants like dried milk, and discusses the economic challenges of making recycling profitable by lowering sorting costs below the value of the recovered commodities. He also describes AMP's strategy of selling robots to existing facilities while building its own green-field recycling plants to demonstrate the technology's potential and drive industry reshoring.

    Robotics & autonomyAI & machine learning
    6 chapters

  • The Robot Report Podcast · 50m

    How AMP Robotics is changing recycling; Festo wins GM gripper challenge

    Matanya Horowitz, founder and CEO of AMP Robotics, explains how the company uses AI and custom suction-based grippers to automate recycling sorting, detailing the evolution of their vision system from garage prototypes to industrial scale. He discusses the company's $55 million Series B funding, the impact of COVID-19 on labor shortages, and new data-centric revenue streams for commodity quality assurance. Josh Fox, an applications engineer at Festo USA, describes how his team won the MassRobotics-GM gripper challenge by developing a universal end effector combining Mag Switch magnetic grippers with Festo actuators to handle various sheet metal parts.

    PCB design & layoutIndustrial & consumer product design
    11 chapters

  • People of Packaging · 52m

    22 - Kate Christian from Eco-cycle LIVE The Ms. Frizzle of Recycling!

    Kate Christian, Director of Business Development at Eco-cycle, explains the mechanics of modern recycling, the impact of China's National Sword policy, and the critical importance of consumer behavior. She details how contamination, particularly shrink sleeves on aluminum cans, disrupts automated sorting at Material Recovery Facilities (MRFs) and reduces material value. Christian advocates for Extended Producer Responsibility (EPR) and urges packaging designers to consider end-of-life realities, warning against misleading 'please recycle' labels on non-recyclable components.

    Sustainability & circular productsPackaging design
    5 chapters

The summary, chapters and topics are generated from the episode’s audio by this directory, not written by Hardware to Save a Planet. The episode itself belongs to its publisher.