Brief IA
›

Redwood Uses AI to Sort Batteries with Over 98% Accuracy

Use Cases·Tom Levy·

Redwood Uses AI to Sort Batteries with Over 98% Accuracy

Redwood Uses AI to Sort Batteries with Over 98% Accuracy
Key Takeaways
1Redwood Materials has automated the sorting of used batteries with AI.
2The company claims an identification accuracy of over 98%.
3The system can process several tons per hour.
Why it matters : Redwood aims to recover metals to reduce its dependence on imports and mining.

Redwood Materials has developed an automated device for sorting used batteries, with identification accuracy exceeding 98% according to the company. The startup, which specializes in battery recycling, was founded by JB Straubel, co-founder of Tesla.

Several Tons Processed Per Hour

Built in just a few months, the equipment can handle several tons per hour. Redwood aims to recover lithium, nickel, and cobalt contained in the batteries. The company intends to reduce its dependence on mining resources and imports.

La lettre du soirGratuit · 19 h

Le brief IA que les pros lisent chaque soir

Les 7 actus IA du jour, décryptées en 5 min. Gratuit.

Inclus dès l'inscription : notre sélection des meilleurs guides & comparatifs IA.

Choisissez votre rythme

Gratuit · Pas de spam · Désabonnement en 1 clic

How AI Identifies Batteries

Before any recycling can take place, sorting must deal with batteries of various sizes, shapes, and chemical compositions. Incompatible mixtures can degrade recycling efficiency or increase costs. Delivered in bulk in bins or boxes, the batteries are first aligned by machines, then pass through a tunnel equipped with sensors and cameras.

The inspection focuses on their weight, shape, and label. The model identifies their category and directs them to the appropriate recycling circuit. Developed by Redwood using a large volume of internal data for training, it operates locally on a set of graphics processors.

Brief IA — L'actualité IA en français

L'essentiel de l'actualité de l'intelligence artificielle, décrypté et expliqué chaque jour.